Tootfinder

PDLRecover: Privacy-preserving Decentralized Model Recovery with Machine Unlearning
Xiangman Li, Xiaodong Wu, Jianbing Ni, Mohamed Mahmoud, Maazen Alsabaan
https://arxiv.org/abs/2506.15112

PDLRecover: Privacy-preserving Decentralized Model Recovery with Machine Unlearning
Decentralized learning is vulnerable to poison attacks, where malicious clients manipulate local updates to degrade global model performance. Existing defenses mainly detect and filter malicious models, aiming to prevent a limited number of attackers from corrupting the global model. However, restoring an already compromised global model remains a challenge. A direct approach is to remove malicious clients and retrain the model using only the benign clients. Yet, retraining is time-consuming, c…

Beyond Shapley Values: Cooperative Games for the Interpretation of Machine Learning Models
Marouane Il Idrissi, Agathe Fernandes Machado, Arthur Charpentier
https://arxiv.org/abs/2506.13900

Beyond Shapley Values: Cooperative Games for the Interpretation of Machine Learning Models
Cooperative game theory has become a cornerstone of post-hoc interpretability in machine learning, largely through the use of Shapley values. Yet, despite their widespread adoption, Shapley-based methods often rest on axiomatic justifications whose relevance to feature attribution remains debatable. In this paper, we revisit cooperative game theory from an interpretability perspective and argue for a broader and more principled use of its tools. We highlight two general families of efficient al…

Enhancement Report Approval Prediction: A Comparative Study of Large Language Models
Haosheng Zuo, Feifei Niu, Chuanyi Li
https://arxiv.org/abs/2506.15098 …

Enhancement Report Approval Prediction: A Comparative Study of Large Language Models
Enhancement reports (ERs) serve as a critical communication channel between users and developers, capturing valuable suggestions for software improvement. However, manually processing these reports is resource-intensive, leading to delays and potential loss of valuable insights. To address this challenge, enhancement report approval prediction (ERAP) has emerged as a research focus, leveraging machine learning techniques to automate decision-making. While traditional approaches have employed fe…

Demonstrating Superresolution in Radar Range Estimation Using a Denoising Autoencoder
Robert Czupryniak, Abhishek Chakraborty, Andrew N. Jordan, John C. Howell
https://arxiv.org/abs/2506.14906

Demonstrating Superresolution in Radar Range Estimation Using a Denoising Autoencoder
We apply machine learning methods to demonstrate range superresolution in remote sensing radar detection. Specifically, we implement a denoising autoencoder to estimate the distance between two equal intensity scatterers in the subwavelength regime. The machine learning models are trained on waveforms subject to a bandlimit constraint such that ranges much smaller than the inverse bandlimit are optimized in their precision. The autoencoder achieves effective dimensionality reduction, with the b…

An introduction to Neural Networks for Physicists
G. Caf\'e de Miranda, Gubio G. de Lima, Tiago de S. Farias
https://arxiv.org/abs/2505.13042 https://

An introduction to Neural Networks for Physicists
Machine learning techniques have emerged as powerful tools to tackle various challenges. The integration of machine learning methods with Physics has led to innovative approaches in understanding, controlling, and simulating physical phenomena. This article aims to provide a practical introduction to neural network and their basic concepts. It presents some perspectives on recent advances at the intersection of machine learning models with physical systems. We introduce practical material to gu…

AIn't Nothing But a Survey? Using Large Language Models for Coding German Open-Ended Survey Responses on Survey Motivation
Leah von der Heyde, Anna-Carolina Haensch, Bernd Wei{\ss}, Jessika Daikeler
https://arxiv.org/abs/2506.14634

AIn't Nothing But a Survey? Using Large Language Models for Coding German Open-Ended Survey Responses on Survey Motivation
The recent development and wider accessibility of LLMs have spurred discussions about how they can be used in survey research, including classifying open-ended survey responses. Due to their linguistic capacities, it is possible that LLMs are an efficient alternative to time-consuming manual coding and the pre-training of supervised machine learning models. As most existing research on this topic has focused on English-language responses relating to non-complex topics or on single LLMs, it is u…

LiteGD: Lightweight and dynamic GPU Dispatching for Large-scale Heterogeneous Clusters
Kunming Zhang, Hanlong Liao, Guoming Tang
https://arxiv.org/abs/2506.15595

LiteGD: Lightweight and dynamic GPU Dispatching for Large-scale Heterogeneous Clusters
Parallel computing with multiple GPUs has become the dominant paradigm for machine learning tasks, especially those of large language models (LLMs). To reduce the latency incurred by inter-GPU communication, a common practice for parallel tasks has been to allocate GPUs based on their physical proximity. However, this long-standing assumption has notable limitations, particularly in large-scale, heterogeneous GPU clusters where bandwidth distribution among GPUs is irregular. In this paper, we i…

Evaluation of machine-learning models to measure individualized treatment effects from randomized clinical trial data with time-to-event outcomes
Elvire Roblin, Paul-Henry Courn\`ede, Stefan Michiels
https://arxiv.org/abs/2506.12277

Evaluation of machine-learning models to measure individualized treatment effects from randomized clinical trial data with time-to-event outcomes
In randomized clinical trials, regression models can be used to explore the relationships between patients' variables (e.g., clinical, pathological or lifestyle variables, and also biomarker or genomics data) and the magnitude of treatment effect. Our aim is to evaluate the value of flexible machine learning models that can incorporate interactions and nonlinear effects of high-dimensional data to estimate individualized treatment recommendations in the setting of such trials with time-to-event…

Embedding physical symmetries into machine-learned reduced plasma physics models via data augmentation
Madox C. McGrae-Menge, Jacob R. Pierce, Frederico Fiuza, E. Paulo Alves
https://arxiv.org/abs/2506.14048

Embedding physical symmetries into machine-learned reduced plasma physics models via data augmentation
Machine learning is offering powerful new tools for the development and discovery of reduced models of nonlinear, multiscale plasma dynamics from the data of first-principles kinetic simulations. However, ensuring the physical consistency of such models requires embedding fundamental symmetries of plasma dynamics. In this work, we explore a symmetry-embedding strategy based on data augmentation, where symmetry-preserving transformations (e.g., Lorentz and Galilean boosts) are applied to simulat…

This https://arxiv.org/abs/2505.09619 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

Predictive Models for Chronic Heart Failure
The management of chronic Heart Failure (HF) presents significant challenges in modern healthcare, requiring continuous monitoring, early detection of exacerbations, and personalized treatment strategies. In this paper, we present a predictive model founded on Machine Learning (ML) techniques to identify patients at HF risk. This model is an ensemble learning approach, a modified stacking technique, that uses two specialized models leveraging clinical and echocardiographic features and then a m…

Hierarchical Deep Feature Fusion and Ensemble Learning for Enhanced Brain Tumor MRI Classification
Zahid Ullah, Jihie Kim
https://arxiv.org/abs/2506.12363 …

Hierarchical Deep Feature Fusion and Ensemble Learning for Enhanced Brain Tumor MRI Classification
Accurate brain tumor classification is crucial in medical imaging to ensure reliable diagnosis and effective treatment planning. This study introduces a novel double ensembling framework that synergistically combines pre-trained deep learning (DL) models for feature extraction with optimized machine learning (ML) classifiers for robust classification. The framework incorporates comprehensive preprocessing and data augmentation of brain magnetic resonance images (MRI), followed by deep feature e…

Humans, Machine Learning, and Language Models in Union: A Cognitive Study on Table Unionability
Sreeram Marimuthu, Nina Klimenkova, Roee Shraga
https://arxiv.org/abs/2506.12990

Humans, Machine Learning, and Language Models in Union: A Cognitive Study on Table Unionability
Data discovery and table unionability in particular became key tasks in modern Data Science. However, the human perspective for these tasks is still under-explored. Thus, this research investigates the human behavior in determining table unionability within data discovery. We have designed an experimental survey and conducted a comprehensive analysis, in which we assess human decision-making for table unionability. We use the observations from the analysis to develop a machine learning framewor…

A Hybrid Neural Network -- Polynomial Series Scheme for Learning Invariant Manifolds of Discrete Dynamical Systems
Dimitrios G. Patsatzis, Nikolaos Kazantzis, Ioannis G. Kevrekidis, Constantinos Siettos
https://arxiv.org/abs/2506.13950

A Hybrid Neural Network -- Polynomial Series Scheme for Learning Invariant Manifolds of Discrete Dynamical Systems
We propose a hybrid machine learning scheme to learn -- in physics-informed and numerical analysis-informed fashion -- invariant manifolds (IM) of discrete maps for constructing reduced-order models (ROMs) for dynamical systems. The proposed scheme combines polynomial series with shallow neural networks, exploiting the complementary strengths of both approaches. Polynomials enable an efficient and accurate modeling of ROMs with guaranteed local exponential convergence rate around the fixed poin…

Rademacher learning rates for iterated random functions
Nikola Sandri\'c
https://arxiv.org/abs/2506.13946 https://arxiv.org/pdf/2…

Rademacher learning rates for iterated random functions
Most existing literature on supervised machine learning assumes that the training dataset is drawn from an i.i.d. sample. However, many real-world problems exhibit temporal dependence and strong correlations between the marginal distributions of the data-generating process, suggesting that the i.i.d. assumption is often unrealistic. In such cases, models naturally include time-series processes with mixing properties, as well as irreducible and aperiodic ergodic Markov chains. Moreover, the lear…

Evaluating Large Language Models for Phishing Detection, Self-Consistency, Faithfulness, and Explainability
Shova Kuikel, Aritran Piplai, Palvi Aggarwal
https://arxiv.org/abs/2506.13746

Evaluating Large Language Models for Phishing Detection, Self-Consistency, Faithfulness, and Explainability
Phishing attacks remain one of the most prevalent and persistent cybersecurity threat with attackers continuously evolving and intensifying tactics to evade the general detection system. Despite significant advances in artificial intelligence and machine learning, faithfully reproducing the interpretable reasoning with classification and explainability that underpin phishing judgments remains challenging. Due to recent advancement in Natural Language Processing, Large Language Models (LLMs) sho…

Evaluation of Machine Learning Models in Student Academic Performance Prediction
A. G. R. Sandeepa, Sanka Mohottala
https://arxiv.org/abs/2506.08047 https:…

Evaluation of Machine Learning Models in Student Academic Performance Prediction
This research investigates the use of machine learning methods to forecast students' academic performance in a school setting. Students' data with behavioral, academic, and demographic details were used in implementations with standard classical machine learning models including multi-layer perceptron classifier (MLPC). MLPC obtained 86.46% maximum accuracy for test set across all implementations. Under 10-fold cross validation, MLPC obtained 79.58% average accuracy for test set while for train…

SINDybrid: automatic generation of hybrid models for dynamic systems
Ulderico Di Caprio, M. Enis Leblebici
https://arxiv.org/abs/2506.12498 https://…

SINDybrid: automatic generation of hybrid models for dynamic systems
Hybrid modelling enhances the accuracy and predictive capability of dynamic models by integrating first principles with data-driven methods, effectively mitigating epistemic uncertainties inherent in mechanistic approaches. However, hybrid model construction remains complex, typically requiring expert knowledge to identify model epistemic uncertainty and select suitable machine-learning components to capture it. This complexity limits broader adoption in research and industry. We introduce SIND…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[2/5]:
Foundation Models for Anomaly Detection: Vision and Challenges
https://

Treasure Hunt: Real-time Targeting of the Long Tail using Training-Time Markers
Daniel D'souza, Julia Kreutzer, Adrien Morisot, Ahmet \"Ust\"un, Sara Hooker
https://arxiv.org/abs/2506.14702

Treasure Hunt: Real-time Targeting of the Long Tail using Training-Time Markers
One of the most profound challenges of modern machine learning is performing well on the long-tail of rare and underrepresented features. Large general-purpose models are trained for many tasks, but work best on high-frequency use cases. After training, it is hard to adapt a model to perform well on specific use cases underrepresented in the training corpus. Relying on prompt engineering or few-shot examples to maximize the output quality on a particular test case can be frustrating, as models …

Many are complaining about CISA removing the RSS feed for KEV. Just a reminder: we expose a lot of the API via RSS and Atom in vulnerability-lookup. KEV is included.
🔗 https://www.vulnerability-lookup.org/user-manual/feed-syndication/

High-expressibility Quantum Neural Networks using only classical resources
Marco Maronese, Francesco Ferrari, Matteo Vandelli, Daniele Dragoni
https://arxiv.org/abs/2506.13605

High-expressibility Quantum Neural Networks using only classical resources
Quantum neural networks (QNNs), as currently formulated, are near-term quantum machine learning architectures that leverage parameterized quantum circuits with the aim of improving upon the performance of their classical counterparts. In this work, we show that some desired properties attributed to these models can be efficiently reproduced without necessarily resorting to quantum hardware. We indeed study the expressibility of parametrized quantum circuit commonly used in QNN applications and …

Inferring Material Parameters from Current-Voltage Curves in Organic Solar Cells via Neural-Network-Based Surrogate Models
Eunchi Kim, Paula Hartnagel, Barbara Urbano, Leonard Christen, Thomas Kirchartz
https://arxiv.org/abs/2506.13308

Inferring Material Parameters from Current-Voltage Curves in Organic Solar Cells via Neural-Network-Based Surrogate Models
Machine learning has emerged as a promising approach for estimating material parameters in solar cells. Traditional methods for parameter extraction often rely on time-consuming numerical simulations that fail to capture the full complexity of the parameter space and discard valuable information from suboptimal simulations. In this study, we introduce a novel workflow for parameter estimation in organic solar cells based on a combination of numerical simulations and neural networks. The workflo…

Can We Trust Machine Learning? The Reliability of Features from Open-Source Speech Analysis Tools for Speech Modeling
Tahiya Chowdhury, Veronica Romero
https://arxiv.org/abs/2506.11072

Can We Trust Machine Learning? The Reliability of Features from Open-Source Speech Analysis Tools for Speech Modeling
Machine learning-based behavioral models rely on features extracted from audio-visual recordings. The recordings are processed using open-source tools to extract speech features for classification models. These tools often lack validation to ensure reliability in capturing behaviorally relevant information. This gap raises concerns about reproducibility and fairness across diverse populations and contexts. Speech processing tools, when used outside of their design context, can fail to capture b…

The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity - Apple Machine Learning Research
https://machinelearning.apple.com/research/illusion-of-thinking

The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity
Recent generations of frontier language models have introduced Large Reasoning Models (LRMs) that generate detailed thinking processes…

A deep learning model for chemical shieldings in molecular organic solids including anisotropy
Matthias Kellner, Jacob B. Holmes, Ruben Rodriguez-Madrid, Florian Viscosi, Yuxuan Zhang, Lyndon Emsley, Michele Ceriotti
https://arxiv.org/abs/2506.13146

A deep learning model for chemical shieldings in molecular organic solids including anisotropy
Nuclear Magnetic Resonance (NMR) chemical shifts are powerful probes of local atomic and electronic structure that can be used to resolve the structures of powdered or amorphous molecular solids. Chemical shift driven structure elucidation depends critically on accurate and fast predictions of chemical shieldings, and machine learning (ML) models for shielding predictions are increasingly used as scalable and efficient surrogates for demanding ab initio calculations. However, the prediction acc…

Replaced article(s) found for physics.ao-ph. https://arxiv.org/list/physics.ao-ph/new
[1/1]:
Regional climate risk assessment from climate models using probabilistic machine learning

Random Matrix Theory for Deep Learning: Beyond Eigenvalues of Linear Models
Zhenyu Liao, Michael W. Mahoney
https://arxiv.org/abs/2506.13139 https://

Random Matrix Theory for Deep Learning: Beyond Eigenvalues of Linear Models
Modern Machine Learning (ML) and Deep Neural Networks (DNNs) often operate on high-dimensional data and rely on overparameterized models, where classical low-dimensional intuitions break down. In particular, the proportional regime where the data dimension, sample size, and number of model parameters are all large and comparable, gives rise to novel and sometimes counterintuitive behaviors. This paper extends traditional Random Matrix Theory (RMT) beyond eigenvalue-based analysis of linear mode…

midr: Learning from Black-Box Models by Maximum Interpretation Decomposition
Ryoichi Asashiba, Reiji Kozuma, Hirokazu Iwasawa
https://arxiv.org/abs/2506.08338

midr: Learning from Black-Box Models by Maximum Interpretation Decomposition
The use of appropriate methods of Interpretable Machine Learning (IML) and eXplainable Artificial Intelligence (XAI) is essential for adopting black-box predictive models in fields where model and prediction explainability is required. As a novel tool for interpreting black-box models, we introduce the R package midr, which implements Maximum Interpretation Decomposition (MID). MID is a functional decomposition approach that derives a low-order additive representation of a black-box model by mi…

From Tea Leaves to System Maps: Context-awareness in Monitoring Operational Machine Learning Models
Joran Leest, Claudia Raibulet, Patricia Lago, Ilias Gerostathopoulos
https://arxiv.org/abs/2506.10770

From Tea Leaves to System Maps: Context-awareness in Monitoring Operational Machine Learning Models
Machine learning (ML) models in production do not fail due to statistical anomalies in their input data; they fail due to contextual misalignment -- when their environment deviates from training assumptions, leading to unreliable predictions. Effective ML monitoring requires rich contextual information to move beyond detecting statistical shifts toward meaningful alerts and systematic root-cause analysis. Yet, surprisingly, despite extensive research in ML monitoring and related disciplines (dr…

Learning to Optimize Package Picking for Large-Scale, Real-World Robot Induction
Shuai Li, Azarakhsh Keipour, Sicong Zhao, Srinath Rajagopalan, Charles Swan, Kostas E. Bekris
https://arxiv.org/abs/2506.09765

Learning to Optimize Package Picking for Large-Scale, Real-World Robot Induction
Warehouse automation plays a pivotal role in enhancing operational efficiency, minimizing costs, and improving resilience to workforce variability. While prior research has demonstrated the potential of machine learning (ML) models to increase picking success rates in large-scale robotic fleets by prioritizing high-probability picks and packages, these efforts primarily focused on predicting success probabilities for picks sampled using heuristic methods. Limited attention has been given, howev…

Conditional diffusion models for guided anomaly detection in brain images using fluid-driven anomaly randomization
Ana Lawry Aguila, Peirong Liu, Oula Puonti, Juan Eugenio Iglesias
https://arxiv.org/abs/2506.10233

Conditional diffusion models for guided anomaly detection in brain images using fluid-driven anomaly randomization
Supervised machine learning has enabled accurate pathology detection in brain MRI, but requires training data from diseased subjects that may not be readily available in some scenarios, for example, in the case of rare diseases. Reconstruction-based unsupervised anomaly detection, in particular using diffusion models, has gained popularity in the medical field as it allows for training on healthy images alone, eliminating the need for large disease-specific cohorts. These methods assume that a …

Simulating realistic radio continuum survey maps with diffusion models
Tobias Vi\v{c}\'anek Mart\'inez, Henrik W. Edler, Marcus Br\"uggen
https://arxiv.org/abs/2506.11715

Simulating realistic radio continuum survey maps with diffusion models
The next generation of radio surveys is going to be transformative for cosmology and other aspects of our understanding of astrophysics. Realistic simulations of radio observations are essential for the design and planning of radio surveys. They are employed in the development of methods for tasks, such as data calibration and reduction, automated analysis and statistical studies in cosmology. We implemented a software for machine learning-assisted simulations of realistic surveys with the LOFA…

Differential Privacy in Machine Learning: From Symbolic AI to LLMs
Francisco Aguilera-Mart\'inez, Fernando Berzal
https://arxiv.org/abs/2506.11687 http…

Differential Privacy in Machine Learning: From Symbolic AI to LLMs
Machine learning models should not reveal particular information that is not otherwise accessible. Differential privacy provides a formal framework to mitigate privacy risks by ensuring that the inclusion or exclusion of any single data point does not significantly alter the output of an algorithm, thus limiting the exposure of private information. This survey paper explores the foundational definitions of differential privacy, reviews its original formulations and tracing its evolution through…

Black-Box Edge AI Model Selection with Conformal Latency and Accuracy Guarantees
Anders E. Kal{\o}r, Tomoaki Ohtsuki
https://arxiv.org/abs/2506.11391 https…

Black-Box Edge AI Model Selection with Conformal Latency and Accuracy Guarantees
Edge artificial intelligence (AI) will be a central part of 6G, with powerful edge servers supporting devices in performing machine learning (ML) inference. However, it is challenging to deliver the latency and accuracy guarantees required by 6G applications, such as automated driving and robotics. This stems from the black-box nature of ML models, the complexities of the tasks, and the interplay between transmitted data quality, chosen inference model, and the random wireless channel. This pap…

An Interpretable Machine Learning Approach in Predicting Inflation Using Payments System Data: A Case Study of Indonesia
Wishnu Badrawani
https://arxiv.org/abs/2506.10369

An Interpretable Machine Learning Approach in Predicting Inflation Using Payments System Data: A Case Study of Indonesia
This paper evaluates the performance of prominent machine learning (ML) algorithms in predicting Indonesia's inflation using the payment system, capital market, and macroeconomic data. We compare the forecasting performance of each ML model, namely shrinkage regression, ensemble learning, and super vector regression, to that of the univariate time series ARIMA and SARIMA models. We examine various out-of-bag sample periods in each ML model to determine the appropriate data-splitting ratios for …

Trustworthiness Preservation by Copies of Machine Learning Systems
Leonardo Ceragioli, Giuseppe Primiero
https://arxiv.org/abs/2506.05203 https://

Trustworthiness Preservation by Copies of Machine Learning Systems
A common practice of ML systems development concerns the training of the same model under different data sets, and the use of the same (training and test) sets for different learning models. The first case is a desirable practice for identifying high quality and unbiased training conditions. The latter case coincides with the search for optimal models under a common dataset for training. These differently obtained systems have been considered akin to copies. In the quest for responsible AI, a l…

The use of cross validation in the analysis of designed experiments
Maria L. Weese, Byran J. Smucker, David J. Edwards
https://arxiv.org/abs/2506.14593 htt…

The use of cross validation in the analysis of designed experiments
Cross-validation (CV) is a common method to tune machine learning methods and can be used for model selection in regression as well. Because of the structured nature of small, traditional experimental designs, the literature has warned against using CV in their analysis. The striking increase in the use of machine learning, and thus CV, in the analysis of experimental designs, has led us to empirically study the effectiveness of CV compared to other methods of selecting models in designed exper…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[5/5]:
Explainability of Large Language Models using SMILE: Statistical Model-agnostic Interpretability ...

Understanding Learning Invariance in Deep Linear Networks
Hao Duan, Guido Mont\'ufar
https://arxiv.org/abs/2506.13714 https://arx…

Understanding Learning Invariance in Deep Linear Networks
Equivariant and invariant machine learning models exploit symmetries and structural patterns in data to improve sample efficiency. While empirical studies suggest that data-driven methods such as regularization and data augmentation can perform comparably to explicitly invariant models, theoretical insights remain scarce. In this paper, we provide a theoretical comparison of three approaches for achieving invariance: data augmentation, regularization, and hard-wiring. We focus on mean squared e…

Hybrid Models for Financial Forecasting: Combining Econometric, Machine Learning, and Deep Learning Models
Dominik Stempie\'n, Robert \'Slepaczuk
https://arxiv.org/abs/2505.19617

Hybrid Models for Financial Forecasting: Combining Econometric, Machine Learning, and Deep Learning Models
This research systematically develops and evaluates various hybrid modeling approaches by combining traditional econometric models (ARIMA and ARFIMA models) with machine learning and deep learning techniques (SVM, XGBoost, and LSTM models) to forecast financial time series. The empirical analysis is based on two distinct financial assets: the S&P 500 index and Bitcoin. By incorporating over two decades of daily data for the S&P 500 and almost ten years of Bitcoin data, the study provides a comp…

Advancing Exchange Rate Forecasting: Leveraging Machine Learning and AI for Enhanced Accuracy in Global Financial Markets
Md. Yeasin Rahat, Rajan Das Gupta, Nur Raisa Rahman, Sudipto Roy Pritom, Samiur Rahman Shakir, Md Imrul Hasan Showmick, Md. Jakir Hossen
https://arxiv.org/abs/2506.09851

Advancing Exchange Rate Forecasting: Leveraging Machine Learning and AI for Enhanced Accuracy in Global Financial Markets
The prediction of foreign exchange rates, such as the US Dollar (USD) to Bangladeshi Taka (BDT), plays a pivotal role in global financial markets, influencing trade, investments, and economic stability. This study leverages historical USD/BDT exchange rate data from 2018 to 2023, sourced from Yahoo Finance, to develop advanced machine learning models for accurate forecasting. A Long Short-Term Memory (LSTM) neural network is employed, achieving an exceptional accuracy of 99.449%, a Root Mean Sq…

Observational Insights on DBI K-essence Models Using Machine Learning and Bayesian Analysis
Samit Ganguly, Arijit Panda, Eduardo Guendelman, Debashis Gangopadhyay, Abhijit Bhattacharyya, Goutam Manna
https://arxiv.org/abs/2506.05674

Observational Insights on DBI K-essence Models Using Machine Learning and Bayesian Analysis
We present a comparative observational data analysis of two DBI-type k-essence scalar field models for late-time cosmic acceleration: one treats dark energy with standard matter, while the other unifies dark energy and dark matter within a single scalar field, each governed by distinct non-canonical Lagrangians. The background dynamics are formulated via modified Friedmann and scalar field equations, constrained by Pantheon+ SNe Ia, Hubble, and BAO data, using Bayesian inference (NUTS in NumPyr…

Constraining Nuclear Mass Models Using r-process Observables with Multi-objective Optimization
Mengke Li, Matthew Mumpower, Nicole Vassh, William Samuel Porter, Rebecca Surman
https://arxiv.org/abs/2506.06464

Constraining Nuclear Mass Models Using r-process Observables with Multi-objective Optimization
Predicting nuclear masses is a longstanding challenge. One path forward is machine learning (ML) which trains on experimental data, but can suffer large errors when extrapolating toward neutron-rich species. In nature, such masses shape observables for the rapid neutron capture process (r-process), which in principle could inform ML models. Here we introduce a multi-objective optimization approach using the Pareto Front algorithm. We show that this technique, capable of identifying models which…

Local surrogates for quantum machine learning
Sreeraj Rajindran Nair, Christopher Ferrie
https://arxiv.org/abs/2506.09425 https://arx…

Local surrogates for quantum machine learning
Surrogates have been proposed as classical simulations of the pretrained quantum learning models, which are capable of mimicking the input-output relation inherent in the quantum model. Quantum hardware within this framework is used for training and for generating the classical surrogates. Inference is relegated to the classical surrogate, hence alleviating the extra quantum computational cost once training is done. Taking inspiration from interpretable models, we introduce a local surrogation …

Advances in LLMs with Focus on Reasoning, Adaptability, Efficiency and Ethics
Asifullah khan, Muhammad Zaeem Khan, Saleha Jamshed, Sadia Ahmad, Aleesha Zainab, Kaynat Khatib, Faria Bibi, Abdul Rehman
https://arxiv.org/abs/2506.12365

Advances in LLMs with Focus on Reasoning, Adaptability, Efficiency and Ethics
This survey paper outlines the key developments in the field of Large Language Models (LLMs), such as enhancing their reasoning skills, adaptability to various tasks, increased computational efficiency, and ability to make ethical decisions. The techniques that have been most effective in bridging the gap between human and machine communications include the Chain-of-Thought prompting, Instruction Tuning, and Reinforcement Learning from Human Feedback. The improvements in multimodal learning and…

Mutual-Supervised Learning for Sequential-to-Parallel Code Translation
Changxin Ke, Rui Zhang, Shuo Wang, Li Ding, Guangli Li, Yuanbo Wen, Shuoming Zhang, Ruiyuan Xu, Jin Qin, Jiaming Guo, Chenxi Wang, Ling Li, Qi Guo, Yunji Chen
https://arxiv.org/abs/2506.11153

Mutual-Supervised Learning for Sequential-to-Parallel Code Translation
The rise of GPU-based high-performance computing (HPC) has driven the widespread adoption of parallel programming models such as CUDA. Yet, the inherent complexity of parallel programming creates a demand for the automated sequential-to-parallel approaches. However, data scarcity poses a significant challenge for machine learning-based sequential-to-parallel code translation. Although recent back-translation methods show promise, they still fail to ensure functional equivalence in the translate…

Evaluating Large Language Models for Phishing Detection, Self-Consistency, Faithfulness, and Explainability
Shova Kuikel, Aritran Piplai, Palvi Aggarwal
https://arxiv.org/abs/2506.13746

Evaluating Large Language Models for Phishing Detection, Self-Consistency, Faithfulness, and Explainability
Phishing attacks remain one of the most prevalent and persistent cybersecurity threat with attackers continuously evolving and intensifying tactics to evade the general detection system. Despite significant advances in artificial intelligence and machine learning, faithfully reproducing the interpretable reasoning with classification and explainability that underpin phishing judgments remains challenging. Due to recent advancement in Natural Language Processing, Large Language Models (LLMs) sho…

Predictive Models for Chronic Heart Failure
Pietro Cassieri, Aiman Faiz, Anna Maria De Roberto, Claudio Pascarelli, Gianvito Mitrano, Gianluca Fimiani, Marina Garofano, Christiancarmine Esposito, Genoveffa Tortora, Alessia Bramanti, Giuseppe Scanniello
https://arxiv.org/abs/2505.09619

Predictive Models for Chronic Heart Failure
The management of chronic Heart Failure (HF) presents significant challenges in modern healthcare, requiring continuous monitoring, early detection of exacerbations, and personalized treatment strategies. In this paper, we present a predictive model founded on Machine Learning (ML) techniques to identify patients at HF risk. This model is an ensemble learning approach, a modified stacking technique, that uses two specialized models leveraging clinical and echocardiographic features and then a m…

This https://arxiv.org/abs/2505.21427 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

Policy Induction: Predicting Startup Success via Explainable Memory-Augmented In-Context Learning
Early-stage startup investment is a high-risk endeavor characterized by scarce data and uncertain outcomes. Traditional machine learning approaches often require large, labeled datasets and extensive fine-tuning, yet remain opaque and difficult for domain experts to interpret or improve. In this paper, we propose a transparent and data-efficient investment decision framework powered by memory-augmented large language models (LLMs) using in-context learning (ICL). Central to our method is a natu…

This https://arxiv.org/abs/2409.17800 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csHC_…

Bias Assessment and Data Drift Detection in Medical Image Analysis: A Survey
Machine Learning (ML) models have gained popularity in medical imaging analysis given their expert level performance in many medical domains. To enhance the trustworthiness, acceptance, and regulatory compliance of medical imaging models and to facilitate their integration into clinical settings, we review and categorise methods for ensuring ML reliability, both during development and throughout the model's lifespan. Specifically, we provide an overview of methods assessing models' inner-workin…

Machine Learning-based quadratic closures for non-intrusive Reduced Order Models
Gabriele Codega, Anna Ivagnes, Nicola Demo, Gianluigi Rozza
https://arxiv.org/abs/2506.09830

Machine Learning-based quadratic closures for non-intrusive Reduced Order Models
In the present work, we introduce a data-driven approach to enhance the accuracy of non-intrusive Reduced Order Models (ROMs). In particular, we focus on ROMs built using Proper Orthogonal Decomposition (POD) in an under-resolved and marginally-resolved regime, i.e. when the number of modes employed is not enough to capture the system dynamics. We propose a method to re-introduce the contribution of neglected modes through a quadratic correction term, given by the action of a quadratic operator…

SoK: Machine Unlearning for Large Language Models
Jie Ren, Yue Xing, Yingqian Cui, Charu C. Aggarwal, Hui Liu
https://arxiv.org/abs/2506.09227 https://

SoK: Machine Unlearning for Large Language Models
Large language model (LLM) unlearning has become a critical topic in machine learning, aiming to eliminate the influence of specific training data or knowledge without retraining the model from scratch. A variety of techniques have been proposed, including Gradient Ascent, model editing, and re-steering hidden representations. While existing surveys often organize these methods by their technical characteristics, such classifications tend to overlook a more fundamental dimension: the underlying…

Estimating properties of a homogeneous bounded soil using machine learning models
Konstantinos Kalimeris, Leonidas Mindrinos, Nikolaos Pallikarakis
https://arxiv.org/abs/2506.04256

Estimating properties of a homogeneous bounded soil using machine learning models
This work focuses on estimating soil properties from water moisture measurements. We consider simulated data generated by solving the initial-boundary value problem governing vertical infiltration in a homogeneous, bounded soil profile, with the usage of the Fokas method. To address the parameter identification problem, which is formulated as a two-output regression task, we explore various machine learning models. The performance of each model is assessed under different data conditions: full,…

Adversarial Disentanglement by Backpropagation with Physics-Informed Variational Autoencoder
Ioannis Christoforos Koune, Alice Cicirello
https://arxiv.org/abs/2506.13658

Adversarial Disentanglement by Backpropagation with Physics-Informed Variational Autoencoder
Inference and prediction under partial knowledge of a physical system is challenging, particularly when multiple confounding sources influence the measured response. Explicitly accounting for these influences in physics-based models is often infeasible due to epistemic uncertainty, cost, or time constraints, resulting in models that fail to accurately describe the behavior of the system. On the other hand, data-driven machine learning models such as variational autoencoders are not guaranteed t…

Benchmarking Large Language Models for Polymer Property Predictions
Sonakshi Gupta, Akhlak Mahmood, Shivank Shukla, Rampi Ramprasad
https://arxiv.org/abs/2506.02129

Benchmarking Large Language Models for Polymer Property Predictions
Machine learning has revolutionized polymer science by enabling rapid property prediction and generative design. Large language models (LLMs) offer further opportunities in polymer informatics by simplifying workflows that traditionally rely on large labeled datasets, handcrafted representations, and complex feature engineering. LLMs leverage natural language inputs through transfer learning, eliminating the need for explicit fingerprinting and streamlining training. In this study, we finetune …

Transient Dynamics in Lattices of Differentiating Ring Oscillators
Peter DelMastro, Arjun Karuvally, Hananel Hazan, Hava Siegelmann, Edward Rietman
https://arxiv.org/abs/2506.07253

Transient Dynamics in Lattices of Differentiating Ring Oscillators
Recurrent neural networks (RNNs) are machine learning models widely used for learning temporal relationships. Current state-of-the-art RNNs use integrating or spiking neurons -- two classes of computing units whose outputs depend directly on their internal states -- and accordingly there is a wealth of literature characterizing the behavior of large networks built from these neurons. On the other hand, past research on differentiating neurons, whose outputs are computed from the derivatives of …

Machine learning-based correlation analysis of decadal cyclone intensity with sea surface temperature: data and tutorial
Jingyang Wu, Rohitash Chandra
https://arxiv.org/abs/2506.09254

Machine learning-based correlation analysis of decadal cyclone intensity with sea surface temperature: data and tutorial
The rising number of extreme climate events in the past decades has motivated the need for a thorough consideration of tropical cyclone genesis and intensity, given the sea-surface temperature (SST). In this paper, we present an analysis of the relationship between the increasing global SST with cyclone genesis using linear regression machine learning models. We extract and curate a dataset of tropical cyclones across selected ocean basins with their associated SST over the past 40 years. We pr…

This https://arxiv.org/abs/2502.03578 has been replaced.
initial toot: https://mastoxiv.page/@a…

Universal machine learning interatomic potentials poised to supplant DFT in modeling general defects in metals and random alloys
Recent advances in machine learning, combined with the generation of extensive density functional theory (DFT) datasets, have enabled the development of universal machine learning interatomic potentials (uMLIPs). These models offer broad applicability across the periodic table, achieving first-principles accuracy at a fraction of the computational cost of traditional DFT calculations. In this study, we demonstrate that state-of-the-art pretrained uMLIPs can effectively replace DFT for accuratel…

Explaining Risks: Axiomatic Risk Attributions for Financial Models
Dangxing Chen
https://arxiv.org/abs/2506.06653 https://arxiv.org/p…

Explaining Risks: Axiomatic Risk Attributions for Financial Models
In recent years, machine learning models have achieved great success at the expense of highly complex black-box structures. By using axiomatic attribution methods, we can fairly allocate the contributions of each feature, thus allowing us to interpret the model predictions. In high-risk sectors such as finance, risk is just as important as mean predictions. Throughout this work, we address the following risk attribution problem: how to fairly allocate the risk given a model with data? We demons…

EUNIS Habitat Maps: Enhancing Thematic and Spatial Resolution for Europe through Machine Learning
Sara Si-Moussi, Stephan Hennekens, Sander M\"ucher, Wanda De Keersmaecker, Milan Chytr\'y, Emiliano Agrillo, Fabio Attorre, Idoia Biurrun, Gianmaria Bonari, Andra\v{z} \v{C}arni, Renata \'Cu\v{s}terevska, Tetiana Dziuba, Klaus Ecker, Behl\"ul G\"uler, Ute Jandt, Borja Jim\'enez-Alfaro, Jonathan Lenoir, Jens-Christian Svenning, Grzegorz Swacha, Wilfried Thuiller

EUNIS Habitat Maps: Enhancing Thematic and Spatial Resolution for Europe through Machine Learning
The EUNIS habitat classification is crucial for categorising European habitats, supporting European policy on nature conservation and implementing the Nature Restoration Law. To meet the growing demand for detailed and accurate habitat information, we provide spatial predictions for 260 EUNIS habitat types at hierarchical level 3, together with independent validation and uncertainty analyses. Using ensemble machine learning models, together with high-resolution satellite imagery and ecologica…

Advances in Small-Footprint Keyword Spotting: A Comprehensive Review of Efficient Models and Algorithms
Soumen Garai, Suman Samui
https://arxiv.org/abs/2506.11169

Advances in Small-Footprint Keyword Spotting: A Comprehensive Review of Efficient Models and Algorithms
Small-Footprint Keyword Spotting (SF-KWS) has gained popularity in today's landscape of smart voice-activated devices, smartphones, and Internet of Things (IoT) applications. This surge is attributed to the advancements in Deep Learning, enabling the identification of predefined words or keywords from a continuous stream of words. To implement the SF-KWS model on edge devices with low power and limited memory in real-world scenarios, a efficient Tiny Machine Learning (TinyML) framework is essen…

Congestion-Aware Path Selection for Load Balancing in AI Clusters
Erfan Nosrati, Majid Ghaderi
https://arxiv.org/abs/2506.08132 https://

Congestion-Aware Path Selection for Load Balancing in AI Clusters
Fast training of large machine learning models requires distributed training on AI clusters consisting of thousands of GPUs. The efficiency of distributed training crucially depends on the efficiency of the network interconnecting GPUs in the cluster. These networks are commonly built using RDMA following a Clos-like datacenter topology. To efficiently utilize the network bandwidth, load balancing is employed to distribute traffic across multiple redundant paths. While there exists numerous tec…

Out of Tune: Demystifying Noise-Effects on Quantum Fourier Models
Maja Franz, Melvin Strobl, Leonid Chaichenets, Eileen Kuehn, Achim Streit, Wolfgang Mauerer
https://arxiv.org/abs/2506.09527

Out of Tune: Demystifying Noise-Effects on Quantum Fourier Models
The field of variational quantum algorithms, in particular quantum machine learning (QML), produced numerous theoretical and empirical insights in recent years. As variational quantum circuits (VQCs) can be represented by Fourier series that contain an exponentially large spectrum in the number of input features, hope for quantum advantage remains. Nevertheless, properties of quantum Fourier models (QFMs) are not yet fully understood, in particular how they could potentially outperform classica…

Big Data-Driven Fraud Detection Using Machine Learning and Real-Time Stream Processing
Chen Liu, Hengyu Tang, Zhixiao Yang, Ke Zhou, Sangwhan Cha
https://arxiv.org/abs/2506.02008 …

Big Data-Driven Fraud Detection Using Machine Learning and Real-Time Stream Processing
In the age of digital finance, detecting fraudulent transactions and money laundering is critical for financial institutions. This paper presents a scalable and efficient solution using Big Data tools and machine learning models. We utilize realtime data streaming platforms like Apache Kafka and Flink, distributed processing frameworks such as Apache Spark, and cloud storage services AWS S3 and RDS. A synthetic dataset representing real-world Anti-Money Laundering (AML) challenges is employed t…

When Forgetting Triggers Backdoors: A Clean Unlearning Attack
Marco Arazzi, Antonino Nocera, Vinod P
https://arxiv.org/abs/2506.12522 https://

When Forgetting Triggers Backdoors: A Clean Unlearning Attack
Machine unlearning has emerged as a key component in ensuring ``Right to be Forgotten'', enabling the removal of specific data points from trained models. However, even when the unlearning is performed without poisoning the forget-set (clean unlearning), it can be exploited for stealthy attacks that existing defenses struggle to detect. In this paper, we propose a novel {\em clean} backdoor attack that exploits both the model learning phase and the subsequent unlearning requests. Unlike traditi…

Prompt-Guided Latent Diffusion with Predictive Class Conditioning for 3D Prostate MRI Generation
Emerson P. Grabke, Masoom A. Haider, Babak Taati
https://arxiv.org/abs/2506.10230 …

Prompt-Guided Latent Diffusion with Predictive Class Conditioning for 3D Prostate MRI Generation
Latent diffusion models (LDM) could alleviate data scarcity challenges affecting machine learning development for medical imaging. However, medical LDM training typically relies on performance- or scientific accessibility-limiting strategies including a reliance on short-prompt text encoders, the reuse of non-medical LDMs, or a requirement for fine-tuning with large data volumes. We propose a Class-Conditioned Efficient Large Language model Adapter (CCELLA) to address these limitations. CCELLA …

Evasion Attacks Against Bayesian Predictive Models
Pablo G. Arce, Roi Naveiro, David R\'ios Insua
https://arxiv.org/abs/2506.09640 https://

Evasion Attacks Against Bayesian Predictive Models
There is an increasing interest in analyzing the behavior of machine learning systems against adversarial attacks. However, most of the research in adversarial machine learning has focused on studying weaknesses against evasion or poisoning attacks to predictive models in classical setups, with the susceptibility of Bayesian predictive models to attacks remaining underexplored. This paper introduces a general methodology for designing optimal evasion attacks against such models. We investigate …

Frugal Machine Learning for Energy-efficient, and Resource-aware Artificial Intelligence
John Violos, Konstantina-Christina Diamanti, Ioannis Kompatsiaris, Symeon Papadopoulos
https://arxiv.org/abs/2506.01869

Frugal Machine Learning for Energy-efficient, and Resource-aware Artificial Intelligence
Frugal Machine Learning (FML) refers to the practice of designing Machine Learning (ML) models that are efficient, cost-effective, and mindful of resource constraints. This field aims to achieve acceptable performance while minimizing the use of computational resources, time, energy, and data for both training and inference. FML strategies can be broadly categorized into input frugality, learning process frugality, and model frugality, each focusing on reducing resource consumption at different…

Differentially Private Distribution Release of Gaussian Mixture Models via KL-Divergence Minimization
Hang Liu, Anna Scaglione, Sean Peisert
https://arxiv.org/abs/2506.03467

Differentially Private Distribution Release of Gaussian Mixture Models via KL-Divergence Minimization
Gaussian Mixture Models (GMMs) are widely used statistical models for representing multi-modal data distributions, with numerous applications in data mining, pattern recognition, data simulation, and machine learning. However, recent research has shown that releasing GMM parameters poses significant privacy risks, potentially exposing sensitive information about the underlying data. In this paper, we address the challenge of releasing GMM parameters while ensuring differential privacy (DP) guar…

This https://arxiv.org/abs/2506.03780 has been replaced.
link: https://scholar.google.com/scholar?q=a

High-Dimensional Learning in Finance
Recent advances in machine learning have shown promising results for financial prediction using large, over-parameterized models. This paper provides theoretical foundations and empirical validation for understanding when and how these methods achieve predictive success. I examine three key aspects of high-dimensional learning in finance. First, I prove that within-sample standardization in Random Fourier Features implementations fundamentally alters the underlying Gaussian kernel approximation…

Enforcing tail calibration when training probabilistic forecast models
Jakob Benjamin Wessel, Maybritt Schillinger, Frank Kwasniok, Sam Allen
https://arxiv.org/abs/2506.13687

Enforcing tail calibration when training probabilistic forecast models
Probabilistic forecasts are typically obtained using state-of-the-art statistical and machine learning models, with model parameters estimated by optimizing a proper scoring rule over a set of training data. If the model class is not correctly specified, then the learned model will not necessarily issue forecasts that are calibrated. Calibrated forecasts allow users to appropriately balance risks in decision making, and it is particularly important that forecast models issue calibrated predicti…

Comparing classical and machine learning force fields for modeling deformation of solid sorbents relevant for direct air capture
Logan M. Brabson, Andrew J. Medford, David S. Sholl
https://arxiv.org/abs/2506.09256

Comparing classical and machine learning force fields for modeling deformation of solid sorbents relevant for direct air capture
Direct air capture (DAC) with solid sorbents such as metal-organic frameworks (MOFs) is a promising approach for negative carbon emissions. Computational materials screening can help identify promising materials from the vast chemical space of potential sorbents. Experiments have shown that MOF framework flexibility and deformation induced by adsorbate molecules can drastically affect adsorption properties such as capacity and selectivity. Force field (FF) models are commonly used as surrogates…

A multi-scale loss formulation for learning a probabilistic model with proper score optimisation
Simon Lang, Martin Leutbecher, Pedro Maciel
https://arxiv.org/abs/2506.10868

A multi-scale loss formulation for learning a probabilistic model with proper score optimisation
We assess the impact of a multi-scale loss formulation for training probabilistic machine-learned weather forecasting models. The multi-scale loss is tested in AIFS-CRPS, a machine-learned weather forecasting model developed at the European Centre for Medium-Range Weather Forecasts (ECMWF). AIFS-CRPS is trained by directly optimising the almost fair continuous ranked probability score (afCRPS). The multi-scale loss better constrains small scale variability without negatively impacting forecast …

A weighted quantum ensemble of homogeneous quantum classifiers
Emiliano Tolotti, Enrico Blanzieri, Davide Pastorello
https://arxiv.org/abs/2506.07810 https…

A weighted quantum ensemble of homogeneous quantum classifiers
Ensemble methods in machine learning aim to improve prediction accuracy by combining multiple models. This is achieved by ensuring diversity among predictors to capture different data aspects. Homogeneous ensembles use identical models, achieving diversity through different data subsets, and weighted-average ensembles assign higher influence to more accurate models through a weight learning procedure. We propose a method to achieve a weighted homogeneous quantum ensemble using quantum classifie…

Missing Data in Signal Processing and Machine Learning: Models, Methods and Modern Approaches
A. Hippert-Ferrer, A. Sportisse, A. Javaheri, M. N. El Korso, D. P. Palomar
https://arxiv.org/abs/2506.01696

Missing Data in Signal Processing and Machine Learning: Models, Methods and Modern Approaches
The goal of this tutorial is to provide an overview of recent methods for handling missing data in signal processing methods, from their origins to the challenges ahead. Missing data approaches are grouped by three main categories: i) missing-data imputation, ii) estimation with missing values and iii) prediction with missing values. We focus on methodological and experimental results through specific case studies on real-world applications. Promising and future research directions, including a…

Can Large Language Models Trigger a Paradigm Shift in Travel Behavior Modeling? Experiences with Modeling Travel Satisfaction
Pengfei Xu, Donggen Wang
https://arxiv.org/abs/2505.23262

Can Large Language Models Trigger a Paradigm Shift in Travel Behavior Modeling? Experiences with Modeling Travel Satisfaction
As a specific domain of subjective well-being, travel satisfaction has attracted much research attention recently. Previous studies primarily use statistical models and, more recently, machine learning models to explore the determinants of travel satisfaction. Both approaches require data from sufficient sample sizes and correct prior statistical assumptions. The emergence of Large Language Models (LLMs) offers a new modeling approach that can overcome the shortcomings of the existing methods. …

Diffusion Models for Increasing Accuracy in Olfaction Sensors and Datasets
Kordel K. France, Ovidiu Daescu
https://arxiv.org/abs/2506.00455 https://…

Diffusion Models for Increasing Accuracy in Olfaction Sensors and Datasets
Robotic odour source localization (OSL) is a critical capability for autonomous systems operating in complex environments. However, current OSL methods often suffer from ambiguities, particularly when robots misattribute odours to incorrect objects due to limitations in olfactory datasets and sensor resolutions. To address this challenge, we introduce a novel machine learning method using diffusion-based molecular generation to enhance odour localization accuracy that can be used by itself or w…

Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning
Hasin Us Sami, Swapneel Sen, Amit K. Roy-Chowdhury, Srikanth V. Krishnamurthy, Basak Guler
https://arxiv.org/abs/2506.04453

Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning
Federated learning (FL) allows multiple data-owners to collaboratively train machine learning models by exchanging local gradients, while keeping their private data on-device. To simultaneously enhance privacy and training efficiency, recently parameter-efficient fine-tuning (PEFT) of large-scale pretrained models has gained substantial attention in FL. While keeping a pretrained (backbone) model frozen, each user fine-tunes only a few lightweight modules to be used in conjunction, to fit speci…

BugGen: A Self-Correcting Multi-Agent LLM Pipeline for Realistic RTL Bug Synthesis
Surya Jasper, Minh Luu, Evan Pan, Aakash Tyagi, Michael Quinn, Jiang Hu, David Kebo Houngninou
https://arxiv.org/abs/2506.10501

BugGen: A Self-Correcting Multi-Agent LLM Pipeline for Realistic RTL Bug Synthesis
Hardware complexity continues to strain verification resources, motivating the adoption of machine learning (ML) methods to improve debug efficiency. However, ML-assisted debugging critically depends on diverse and scalable bug datasets, which existing manual or automated bug insertion methods fail to reliably produce. We introduce BugGen, a first of its kind, fully autonomous, multi-agent pipeline leveraging Large Language Models (LLMs) to systematically generate, insert, and validate realisti…

Flexible and Efficient Drift Detection without Labels
Nelvin Tan, Yu-Ching Shih, Dong Yang, Amol Salunkhe
https://arxiv.org/abs/2506.08734 https://

Flexible and Efficient Drift Detection without Labels
Machine learning models are being increasingly used to automate decisions in almost every domain, and ensuring the performance of these models is crucial for ensuring high quality machine learning enabled services. Ensuring concept drift is detected early is thus of the highest importance. A lot of research on concept drift has focused on the supervised case that assumes the true labels of supervised tasks are available immediately after making predictions. Controlling for false positives while…

This https://arxiv.org/abs/2402.10686 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIT_…

On the Impact of Uncertainty and Calibration on Likelihood-Ratio Membership Inference Attacks
In a membership inference attack (MIA), an attacker exploits the overconfidence exhibited by typical machine learning models to determine whether a specific data point was used to train a target model. In this paper, we analyze the performance of the likelihood ratio attack (LiRA) within an information-theoretical framework that allows the investigation of the impact of the aleatoric uncertainty in the true data generation process, of the epistemic uncertainty caused by a limited training data …

Adversarial Surrogate Risk Bounds for Binary Classification
Natalie S. Frank
https://arxiv.org/abs/2506.09348 https://arxiv.org/pdf/2…

Adversarial Surrogate Risk Bounds for Binary Classification
A central concern in classification is the vulnerability of machine learning models to adversarial attacks. Adversarial training is one of the most popular techniques for training robust classifiers, which involves minimizing an adversarial surrogate risk. Recent work characterized when a minimizing sequence of an adversarial surrogate risk is also a minimizing sequence of the adversarial classification risk for binary classification -- a property known as adversarial consistency. However, thes…

Model Splitting Enhanced Communication-Efficient Federated Learning for CSI Feedback
Yanjie Dong, Haijun Zhang, Gaojie Chen, Xiaoyi Fan, Victor C. M. Leung, Xiping Hu
https://arxiv.org/abs/2506.04113

Model Splitting Enhanced Communication-Efficient Federated Learning for CSI Feedback
Recent advancements have introduced federated machine learning-based channel state information (CSI) compression before the user equipments (UEs) upload the downlink CSI to the base transceiver station (BTS). However, most existing algorithms impose a high communication overhead due to frequent parameter exchanges between UEs and BTS. In this work, we propose a model splitting approach with a shared model at the BTS and multiple local models at the UEs to reduce communication overhead. Moreover…

Evaluating Query Efficiency and Accuracy of Transfer Learning-based Model Extraction Attack in Federated Learning
Sayyed Farid Ahamed, Sandip Roy, Soumya Banerjee, Marc Vucovich, Kevin Choi, Abdul Rahman, Alison Hu, Edward Bowen, Sachin Shetty
https://arxiv.org/abs/2505.23791

Evaluating Query Efficiency and Accuracy of Transfer Learning-based Model Extraction Attack in Federated Learning
Federated Learning (FL) is a collaborative learning framework designed to protect client data, yet it remains highly vulnerable to Intellectual Property (IP) threats. Model extraction (ME) attacks pose a significant risk to Machine Learning as a Service (MLaaS) platforms, enabling attackers to replicate confidential models by querying black-box (without internal insight) APIs. Despite FL's privacy-preserving goals, its distributed nature makes it particularly susceptible to such attacks. This p…

Applying Large Language Models to Issue Classification: Revisiting with Extended Data and New Models
Gabriel Aracena, Kyle Luster, Fabio Santos, Igor Steinmacher, Marco A. Gerosa
https://arxiv.org/abs/2506.00128

Applying Large Language Models to Issue Classification: Revisiting with Extended Data and New Models
Effective prioritization of issue reports in software engineering helps to optimize resource allocation and information recovery. However, manual issue classification is laborious and lacks scalability. As an alternative, many open source software (OSS) projects employ automated processes for this task, yet this method often relies on large datasets for adequate training. Traditionally, machine learning techniques have been used for issue classification. More recently, large language models (LL…

Learning thermodynamic master equations for open quantum systems
Peter Sentz, Stanley Nicholson, Yujin Cho, Sohail Reddy, Brendan Keith, Stefanie G\"unther
https://arxiv.org/abs/2506.01882

Learning thermodynamic master equations for open quantum systems
The characterization of Hamiltonians and other components of open quantum dynamical systems plays a crucial role in quantum computing and other applications. Scientific machine learning techniques have been applied to this problem in a variety of ways, including by modeling with deep neural networks. However, the majority of mathematical models describing open quantum systems are linear, and the natural nonlinearities in learnable models have not been incorporated using physical principles. We …

This https://arxiv.org/abs/2505.12887 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

RetinaLogos: Fine-Grained Synthesis of High-Resolution Retinal Images Through Captions
The scarcity of high-quality, labelled retinal imaging data, which presents a significant challenge in the development of machine learning models for ophthalmology, hinders progress in the field. To synthesise Colour Fundus Photographs (CFPs), existing methods primarily relying on predefined disease labels face significant limitations. However, current methods remain limited, thus failing to generate images for broader categories with diverse and fine-grained anatomical structures. To overcome …

Memory Access Characterization of Large Language Models in CPU Environment and its Potential Impacts
Spencer Banasik
https://arxiv.org/abs/2506.01827 https…

Memory Access Characterization of Large Language Models in CPU Environment and its Potential Impacts
As machine learning algorithms are shown to be an increasingly valuable tool, the demand for their access has grown accordingly. Oftentimes, it is infeasible to run inference with larger models without an accelerator, which may be unavailable in environments that have constraints such as energy consumption, security, or cost. To increase the availability of these models, we aim to im- prove the LLM inference speed on a CPU-only environment by modifying the cache architecture. To determine what …

Box-Constrained Softmax Function and Its Application for Post-Hoc Calibration
Kyohei Atarashi, Satoshi Oyama, Hiromi Arai, Hisashi Kashima
https://arxiv.org/abs/2506.10572

Box-Constrained Softmax Function and Its Application for Post-Hoc Calibration
Controlling the output probabilities of softmax-based models is a common problem in modern machine learning. Although the $\mathrm{Softmax}$ function provides soft control via its temperature parameter, it lacks the ability to enforce hard constraints, such as box constraints, on output probabilities, which can be critical in certain applications requiring reliable and trustworthy models. In this work, we propose the box-constrained softmax ($\mathrm{BCSoftmax}$) function, a novel generalizatio…

A Quantum Information Theoretic Approach to Tractable Probabilistic Models
Pedro Zuidberg Dos Martires
https://arxiv.org/abs/2506.01824 https://

A Quantum Information Theoretic Approach to Tractable Probabilistic Models
By recursively nesting sums and products, probabilistic circuits have emerged in recent years as an attractive class of generative models as they enjoy, for instance, polytime marginalization of random variables. In this work we study these machine learning models using the framework of quantum information theory, leading to the introduction of positive unital circuits (PUnCs), which generalize circuit evaluations over positive real-valued probabilities to circuit evaluations over positive semi…

This https://arxiv.org/abs/2503.09128 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

FlexiReg: Flexible Urban Region Representation Learning
The increasing availability of urban data offers new opportunities for learning region representations, which can be used as input to machine learning models for downstream tasks such as check-in or crime prediction. While existing solutions have produced promising results, an issue is their fixed formation of regions and fixed input region features, which may not suit the needs of different downstream tasks. To address this limitation, we propose a model named FlexiReg for urban region represe…

How do Pre-Trained Models Support Software Engineering? An Empirical Study in Hugging Face
Alexandra Gonz\'alez, Xavier Franch, David Lo, Silverio Mart\'inez-Fern\'andez
https://arxiv.org/abs/2506.03013

How do Pre-Trained Models Support Software Engineering? An Empirical Study in Hugging Face
Open-Source Pre-Trained Models (PTMs) provide extensive resources for various Machine Learning (ML) tasks, yet these resources lack a classification tailored to Software Engineering (SE) needs. To address this gap, we derive a taxonomy encompassing 147 SE tasks and apply an SE-oriented classification to PTMs in a popular open-source ML repository, Hugging Face (HF). Our repository mining study began with a systematically gathered database of PTMs from the HF API, considering their model card de…

This https://arxiv.org/abs/2312.01602 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qu…

Quantum Time Series Similarity Measures and Quantum Temporal Kernels
This article presents a quantum computing approach to designing of similarity measures and kernels for classification of stochastic symbolic time series. In the area of machine learning, kernels are important components of various similarity-based classification, clustering, and regression algorithms. An effective strategy for devising problem-specific kernels is leveraging existing generative models of the example space. In this study we assume that a quantum generative model, known as quantum…

carps: A Framework for Comparing N Hyperparameter Optimizers on M Benchmarks
Carolin Benjamins, Helena Graf, Sarah Segel, Difan Deng, Tim Ruhkopf, Leona Hennig, Soham Basu, Neeratyoy Mallik, Edward Bergman, Deyao Chen, Fran\c{c}ois Cl\'ement, Matthias Feurer, Katharina Eggensperger, Frank Hutter, Carola Doerr, Marius Lindauer
https://

carps: A Framework for Comparing N Hyperparameter Optimizers on M Benchmarks
Hyperparameter Optimization (HPO) is crucial to develop well-performing machine learning models. In order to ease prototyping and benchmarking of HPO methods, we propose carps, a benchmark framework for Comprehensive Automated Research Performance Studies allowing to evaluate N optimizers on M benchmark tasks. In this first release of carps, we focus on the four most important types of HPO task types: blackbox, multi-fidelity, multi-objective and multi-fidelity-multi-objective. With 3 336 tasks…

Stealix: Model Stealing via Prompt Evolution
Zhixiong Zhuang, Hui-Po Wang, Maria-Irina Nicolae, Mario Fritz
https://arxiv.org/abs/2506.05867 https://

Stealix: Model Stealing via Prompt Evolution
Model stealing poses a significant security risk in machine learning by enabling attackers to replicate a black-box model without access to its training data, thus jeopardizing intellectual property and exposing sensitive information. Recent methods that use pre-trained diffusion models for data synthesis improve efficiency and performance but rely heavily on manually crafted prompts, limiting automation and scalability, especially for attackers with little expertise. To assess the risks posed …

This https://arxiv.org/abs/2405.06003 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

Binary Hypothesis Testing for Softmax Models and Leverage Score Models
Softmax distributions are widely used in machine learning, including Large Language Models (LLMs), where the attention unit uses softmax distributions. We abstract the attention unit as the softmax model, where given a vector input, the model produces an output drawn from the softmax distribution (which depends on the vector input). We consider the fundamental problem of binary hypothesis testing in the setting of softmax models. That is, given an unknown softmax model, which is known to be one…

Synthesis of discrete-continuous quantum circuits with multimodal diffusion models
Florian F\"urrutter, Zohim Chandani, Ikko Hamamura, Hans J. Briegel, Gorka Mu\~noz-Gil
https://arxiv.org/abs/2506.01666

Synthesis of discrete-continuous quantum circuits with multimodal diffusion models
Efficiently compiling quantum operations remains a major bottleneck in scaling quantum computing. Today's state-of-the-art methods achieve low compilation error by combining search algorithms with gradient-based parameter optimization, but they incur long runtimes and require multiple calls to quantum hardware or expensive classical simulations, making their scaling prohibitive. Recently, machine-learning models have emerged as an alternative, though they are currently restricted to discrete ga…

Synthetic Tabular Data: Methods, Attacks and Defenses
Graham Cormode, Samuel Maddock, Enayat Ullah, Shripad Gade
https://arxiv.org/abs/2506.06108 https://

Synthetic Tabular Data: Methods, Attacks and Defenses
Synthetic data is often positioned as a solution to replace sensitive fixed-size datasets with a source of unlimited matching data, freed from privacy concerns. There has been much progress in synthetic data generation over the last decade, leveraging corresponding advances in machine learning and data analytics. In this survey, we cover the key developments and the main concepts in tabular synthetic data generation, including paradigms based on probabilistic graphical models and on deep learni…

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models
Xueqi Cheng, Minxing Zheng, Shixiang Zhu, Yushun Dong
https://arxiv.org/abs/2506.02362

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models
Model extraction attacks aim to replicate the functionality of a black-box model through query access, threatening the intellectual property (IP) of machine-learning-as-a-service (MLaaS) providers. Defending against such attacks is challenging, as it must balance efficiency, robustness, and utility preservation in the real-world scenario. Despite the recent advances, most existing defenses presume that attacker queries have out-of-distribution (OOD) samples, enabling them to detect and disrupt …

NepTrain and NepTrainKit: Automated Active Learning and Visualization Toolkit for Neuroevolution Potentials
Chengbing Chen, Yutong Li, Rui Zhao, Zhoulin Liu, Zheyong Fan, Gang Tang, Zhiyong Wang
https://arxiv.org/abs/2506.01868

NepTrain and NepTrainKit: Automated Active Learning and Visualization Toolkit for Neuroevolution Potentials
As a machine-learned potential, the neuroevolution potential (NEP) method features exceptional computational efficiency and has been successfully applied in materials science. Constructing high-quality training datasets is crucial for developing accurate NEP models. However, the preparation and screening of NEP training datasets remain a bottleneck for broader applications due to their time-consuming, labor-intensive, and resource-intensive nature. In this work, we have developed NepTrain and N…