Tootfinder

Utilizing Machine Learning and 3D Neuroimaging to Predict Hearing Loss: A Comparative Analysis of Dimensionality Reduction and Regression Techniques
Trinath Sai Subhash Reddy Pittala, Uma Maheswara R Meleti, Manasa Thatipamula
https://arxiv.org/abs/2405.00142

Utilizing Machine Learning and 3D Neuroimaging to Predict Hearing Loss: A Comparative Analysis of Dimensionality Reduction and Regression Techniques
In this project, we have explored machine learning approaches for predicting hearing loss thresholds on the brain's gray matter 3D images. We have solved the problem statement in two phases. In the first phase, we used a 3D CNN model to reduce high-dimensional input into latent space and decode it into an original image to represent the input in rich feature space. In the second phase, we utilized this model to reduce input into rich features and used these features to train standard machine le…

LOQA: Learning with Opponent Q-Learning Awareness
Milad Aghajohari, Juan Agustin Duque, Tim Cooijmans, Aaron Courville
https://arxiv.org/abs/2405.01035 htt…

LOQA: Learning with Opponent Q-Learning Awareness
In various real-world scenarios, interactions among agents often resemble the dynamics of general-sum games, where each agent strives to optimize its own utility. Despite the ubiquitous relevance of such settings, decentralized machine learning algorithms have struggled to find equilibria that maximize individual utility while preserving social welfare. In this paper we introduce Learning with Opponent Q-Learning Awareness (LOQA), a novel, decentralized reinforcement learning algorithm tailored…

Reinforcement Learning for Edit-Based Non-Autoregressive Neural Machine Translation
Hao Wang, Tetsuro Morimura, Ukyo Honda, Daisuke Kawahara
https://arxiv.org/abs/2405.01280

Reinforcement Learning for Edit-Based Non-Autoregressive Neural Machine Translation
Non-autoregressive (NAR) language models are known for their low latency in neural machine translation (NMT). However, a performance gap exists between NAR and autoregressive models due to the large decoding space and difficulty in capturing dependency between target words accurately. Compounding this, preparing appropriate training data for NAR models is a non-trivial task, often exacerbating exposure bias. To address these challenges, we apply reinforcement learning (RL) to Levenshtein Transf…

Python für Umsteiger – Einstieg in die KI-Sprache für Entwickler in 5 Webinaren
Alle reden von KI und Machine Learning – Python bildet dafür die Basis. Lernen Sie in fünf Webinaren ab dem 25.04. diese Sprache zu beherrschen.

$1 TinyML Board For Your “AI” Sensor Swarm
https://poliverso.org/display/0477a01e-efac8092-31813fdbf9039764
$1 TinyML Board For Your “AI” Sensor Swarm You might be under the impression that machine learning costs thousands of dollars to work with. T…

This https://arxiv.org/abs/2307.02091 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qu…

Quantum support vector machines for classification and regression on a trapped-ion quantum computer
Quantum machine learning is a rapidly growing field at the intersection of quantum computing and machine learning. In this work, we examine our quantum machine learning models, which are based on quantum support vector classification (QSVC) and quantum support vector regression (QSVR). We investigate these models using a quantum-circuit simulator, both with and without noise, as well as the IonQ Harmony quantum processor. For the QSVC tasks, we use a dataset containing fraudulent credit card tr…

Endlich bin ich dazu gekommen, eine erste Version einer Grafik online zu stellen, welche versucht, Grundkonzepte des Datenschutzproblems bei generativen Machine-Learning-Systemen aufzuzeigen.
https://gmls.phsz.ch/GMLS/DatenSchutz

Datenschutzaspekte bei ChatGPT & Co.
Datenschutzaspekte bei ChatGPT & Co.

How AI is being used to evaluate the authenticity of paintings, amid conservators' concerns of whether the tech can account for wear, damage, and other factors (Gareth Harris/Financial Times)
https://t.co/jfdyaGqNTn

AI meets Old Masters in the fight to authenticate paintings
Machine learning can be the difference between a charming picture and a masterpiece worth millions

FAIRM: Learning invariant representations for algorithmic fairness and domain generalization with minimax optimality
Sai Li, Linjun Zhang
https://arxiv.org/abs/2404.01608

FAIRM: Learning invariant representations for algorithmic fairness and domain generalization with minimax optimality
Machine learning methods often assume that the test data have the same distribution as the training data. However, this assumption may not hold due to multiple levels of heterogeneity in applications, raising issues in algorithmic fairness and domain generalization. In this work, we address the problem of fair and generalizable machine learning by invariant principles. We propose a training environment-based oracle, FAIRM, which has desirable fairness and domain generalization properties under …

Certified Adversarial Robustness of Machine Learning-based Malware Detectors via (De)Randomized Smoothing
Daniel Gibert, Luca Demetrio, Giulio Zizzo, Quan Le, Jordi Planes, Battista Biggio
https://arxiv.org/abs/2405.00392

Certified Adversarial Robustness of Machine Learning-based Malware Detectors via (De)Randomized Smoothing
Deep learning-based malware detection systems are vulnerable to adversarial EXEmples - carefully-crafted malicious programs that evade detection with minimal perturbation. As such, the community is dedicating effort to develop mechanisms to defend against adversarial EXEmples. However, current randomized smoothing-based defenses are still vulnerable to attacks that inject blocks of adversarial content. In this paper, we introduce a certifiable defense against patch attacks that guarantees, for …

HLSFactory: A Framework Empowering High-Level Synthesis Datasets for Machine Learning and Beyond
Stefan Abi-Karam, Rishov Sarkar, Allison Seigler, Sean Lowe, Zhigang Wei, Hanqiu Chen, Nanditha Rao, Lizy John, Aman Arora, Cong Hao
https://arxiv.org/abs/2405.00820

HLSFactory: A Framework Empowering High-Level Synthesis Datasets for Machine Learning and Beyond
Machine learning (ML) techniques have been applied to high-level synthesis (HLS) flows for quality-of-result (QoR) prediction and design space exploration (DSE). Nevertheless, the scarcity of accessible high-quality HLS datasets and the complexity of building such datasets present challenges. Existing datasets have limitations in terms of benchmark coverage, design space enumeration, vendor extensibility, or lack of reproducible and extensible software for dataset construction. Many works also …

Utilizing Machine Learning and 3D Neuroimaging to Predict Hearing Loss: A Comparative Analysis of Dimensionality Reduction and Regression Techniques
Trinath Sai Subhash Reddy Pittala, Uma Maheswara R Meleti, Manasa Thatipamula
https://arxiv.org/abs/2405.00142

Utilizing Machine Learning and 3D Neuroimaging to Predict Hearing Loss: A Comparative Analysis of Dimensionality Reduction and Regression Techniques
In this project, we have explored machine learning approaches for predicting hearing loss thresholds on the brain's gray matter 3D images. We have solved the problem statement in two phases. In the first phase, we used a 3D CNN model to reduce high-dimensional input into latent space and decode it into an original image to represent the input in rich feature space. In the second phase, we utilized this model to reduce input into rich features and used these features to train standard machine le…

The BSc-level version of my transformers lecture is finished: https://mlvu.github.io/transformers/
Now to record the videos.
This was a nice opportunity to bring the material up to date a bit and show the whole history from self-attention to ChatGPT in one story.

Fusion Dynamical Systems with Machine Learning in Imitation Learning: A Comprehensive Overview
Yingbai Hu, Fares J. Abu-Dakka, Fei Chen, Xiao Luo, Zheng Li, Alois Knoll, Weiping Ding
https://arxiv.org/abs/2403.19916

Fusion Dynamical Systems with Machine Learning in Imitation Learning: A Comprehensive Overview
Imitation Learning (IL), also referred to as Learning from Demonstration (LfD), holds significant promise for capturing expert motor skills through efficient imitation, facilitating adept navigation of complex scenarios. A persistent challenge in IL lies in extending generalization from historical demonstrations, enabling the acquisition of new skills without re-teaching. Dynamical system-based IL (DSIL) emerges as a significant subset of IL methodologies, offering the ability to learn trajecto…

Greater benefits of deep learning-based computer-aided detection systems for finding small signals in 3D volumetric medical images
Devi Klein, Srijita Karmakar, Aditya Jonnalagadda, Craig K. Abbey, Miguel P. Eckstein
https://arxiv.org/abs/2405.00144

Greater benefits of deep learning-based computer-aided detection systems for finding small signals in 3D volumetric medical images
Purpose: Radiologists are tasked with visually scrutinizing large amounts of data produced by 3D volumetric imaging modalities. Small signals can go unnoticed during the 3d search because they are hard to detect in the visual periphery. Recent advances in machine learning and computer vision have led to effective computer-aided detection (CADe) support systems with the potential to mitigate perceptual errors. Approach: Sixteen non-expert observers searched through digital breast tomosynthesis…

Satellite Federated Edge Learning: Architecture Design and Convergence Analysis
Yuanming Shi, Li Zeng, Jingyang Zhu, Yong Zhou, Chunxiao Jiang, Khaled B. Letaief
https://arxiv.org/abs/2404.01875

Satellite Federated Edge Learning: Architecture Design and Convergence Analysis
The proliferation of low-earth-orbit (LEO) satellite networks leads to the generation of vast volumes of remote sensing data which is traditionally transferred to the ground server for centralized processing, raising privacy and bandwidth concerns. Federated edge learning (FEEL), as a distributed machine learning approach, has the potential to address these challenges by sharing only model parameters instead of raw data. Although promising, the dynamics of LEO networks, characterized by the hig…

Still reading takes about the Apple car as though it was just an electric car. Apple was developing a full self-driving vehicle, not merely an electric car with the promise of iterative driving assistance.
Hopefully the millions they spent on machine vision / machine learning (and battery tech) benefits… something.

Scheduling of Distributed Applications on the Computing Continuum: A Survey
Narges Mehran, Dragi Kimovski, Hermann Hellwagner, Dumitru Roman, Ahmet Soylu, Radu Prodan
https://arxiv.org/abs/2405.00005

Scheduling of Distributed Applications on the Computing Continuum: A Survey
The demand for distributed applications has significantly increased over the past decade, with improvements in machine learning techniques fueling this growth. These applications predominantly utilize Cloud data centers for high-performance computing and Fog and Edge devices for low-latency communication for small-size machine learning model training and inference. The challenge of executing applications with different requirements on heterogeneous devices requires effective methods for solving…

This https://arxiv.org/abs/2109.10561 has been replaced.
link: https://scholar.google.com/scholar?q=a

A Few-Shot Learning Approach for Sound Source Distance Estimation Using Relation Networks
In this paper, we study the performance of few-shot learning, specifically meta learning empowered few-shot relation networks, over supervised deep learning and conventional machine learning approaches in the problem of Sound Source Distance Estimation (SSDE). In previous research on deep supervised SSDE, low accuracies have often resulted from the mismatch between the training data (from known environments) and the test data (from unknown environments). By performing comparative experiments on…

This https://arxiv.org/abs/2210.09730 has been replaced.
link: https://scholar.google.com/scholar?q=a

Efficient Syndrome Decoder for Heavy Hexagonal QECC via Machine Learning
Error syndromes for heavy hexagonal code and other topological codes such as surface code have typically been decoded by using Minimum Weight Perfect Matching (MWPM) based methods. Recent advances have shown that topological codes can be efficiently decoded by deploying machine learning (ML) techniques, in particular with neural networks. In this work, we first propose an ML based decoder for heavy hexagonal code and establish its efficiency in terms of the values of threshold and pseudo-thresh…

Convolutional Prompting meets Language Models for Continual Learning
Anurag Roy, Riddhiman Moulick, Vinay K. Verma, Saptarshi Ghosh, Abir Das
https://arxiv.org/abs/2403.20317

Convolutional Prompting meets Language Models for Continual Learning
Continual Learning (CL) enables machine learning models to learn from continuously shifting new training data in absence of data from old tasks. Recently, pretrained vision transformers combined with prompt tuning have shown promise for overcoming catastrophic forgetting in CL. These approaches rely on a pool of learnable prompts which can be inefficient in sharing knowledge across tasks leading to inferior performance. In addition, the lack of fine-grained layer specific prompts does not allow…

This https://arxiv.org/abs/2312.08279 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_…

Energy spectra of elemental groups of cosmic rays with the KASCADE experiment data and machine learning
We report the reconstruction of the mass component spectra of cosmic rays (protons, helium, carbon, silicon and iron) and their mean mass composition, at energies from 1.4 to 100 PeV. The results are derived from the archival data of the extensive air shower experiment KASCADE. We use a novel machine learning technique developed specifically for this reconstruction, and post-LHC hadronic interaction models: QGSJet-II.04, EPOS-LHC and Sibyll 2.3c. We have found an excess of the proton component …

Something I wrote a few years ago in an explainer of #AI from the from the perspective of democracy, rights and governance.
https://www.civicspace.tech/technologies/machine-lea…

I just published "What is Machine Learning?" over on @…. https://jws.news/2024/what-is-machine-learning/

AI has the potential to ease the US meat industry's labor vulnerability by letting robots perform some of the high precision tasks required to butcher meat (Bloomberg)
https://www.bloomberg.com/news/articles/2024-…

AI Is Helping Automate One of the World’s Most Gruesome Jobs
Advances in computer vision and machine learning allow robots to perform some of the high precision tasks required to butcher beef and chicken.

Pricing Catastrophe Bonds -- A Probabilistic Machine Learning Approach
Xiaowei Chen, Hong Li, Yufan Lu, Rui Zhou
https://arxiv.org/abs/2405.00697 https://<…

Pricing Catastrophe Bonds -- A Probabilistic Machine Learning Approach
This paper proposes a probabilistic machine learning method to price catastrophe (CAT) bonds in the primary market. The proposed method combines machine-learning-based predictive models with Conformal Prediction, an innovative algorithm that generates distribution-free probabilistic forecasts for CAT bond prices. Using primary market CAT bond transaction records between January 1999 and March 2021, the proposed method is found to be more robust and yields more accurate predictions of the bond s…

Announcing TransformersPHP: Bring Machine Learning Magic to Your #PHP Projects
#llm #ai

Machine Learning-based Estimation of Respiratory Fluctuations in a Healthy Adult Population using BOLD fMRI and Head Motion Parameters
Abdoljalil Addeh, Fernando Vega, Rebecca J. Williams, G. Bruce Pike, M. Ethan MacDonald
https://arxiv.org/abs/2405.00219

Machine Learning-based Estimation of Respiratory Fluctuations in a Healthy Adult Population using BOLD fMRI and Head Motion Parameters
Motivation: In many fMRI studies, respiratory signals are often missing or of poor quality. Therefore, it could be highly beneficial to have a tool to extract respiratory variation (RV) waveforms directly from fMRI data without the need for peripheral recording devices. Goal(s): Investigate the hypothesis that head motion parameters contain valuable information regarding respiratory patter, which can help machine learning algorithms estimate the RV waveform. Approach: This study proposes a …

This https://arxiv.org/abs/2301.02608 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

An interpretable machine learning system for colorectal cancer diagnosis from pathology slides
Considering the profound transformation affecting pathology practice, we aimed to develop a scalable artificial intelligence (AI) system to diagnose colorectal cancer from whole-slide images (WSI). For this, we propose a deep learning (DL) system that learns from weak labels, a sampling strategy that reduces the number of training samples by a factor of six without compromising performance, an approach to leverage a small subset of fully annotated samples, and a prototype with explainable predi…

PackVFL: Efficient HE Packing for Vertical Federated Learning
Liu Yang, Shuowei Cai, Di Chai, Junxue Zhang, Han Tian, Yilun Jin, Kun Guo, Kai Chen, Qiang Yang
https://arxiv.org/abs/2405.00482

PackVFL: Efficient HE Packing for Vertical Federated Learning
As an essential tool of secure distributed machine learning, vertical federated learning (VFL) based on homomorphic encryption (HE) suffers from severe efficiency problems due to data inflation and time-consuming operations. To this core, we propose PackVFL, an efficient VFL framework based on packed HE (PackedHE), to accelerate the existing HE-based VFL algorithms. PackVFL packs multiple cleartexts into one ciphertext and supports single-instruction-multiple-data (SIMD)-style parallelism. We f…

Introducing the DREAMS Project: DaRk mattEr and Astrophysics with Machine learning and Simulations
Jonah C. Rose, Paul Torrey, Francisco Villaescusa-Navarro, Mariangela Lisanti, Tri Nguyen, Sandip Roy, Kassidy E. Kollmann, Mark Vogelsberger, Francis-Yan Cyr-Racine, Mikhail V. Medvedev, Shy Genel, Daniel Angl\'es-Alc\'azar, Nitya Kallivayalil, Bonny Y. Wang, Bel\'en Costanza, Stephanie O'Neil, Cian Roche, Soumyodipta Karmakar, Alex M. Garcia, Ryan Low, Shurui Lin, Olivia…

Introducing the DREAMS Project: DaRk mattEr and Astrophysics with Machine learning and Simulations
We introduce the DREAMS project, an innovative approach to understanding the astrophysical implications of alternative dark matter models and their effects on galaxy formation and evolution. The DREAMS project will ultimately comprise thousands of cosmological hydrodynamic simulations that simultaneously vary over dark matter physics, astrophysics, and cosmology in modeling a range of systems -- from galaxy clusters to ultra-faint satellites. Such extensive simulation suites can provide adequat…

Modular, Hierarchical Machine Learning for Sequential Goal Completion
Nathan McDonald
https://arxiv.org/abs/2404.19060 https://arxiv.…

Modular, Hierarchical Machine Learning for Sequential Goal Completion
Given a maze populated with different objects, one may task a robot with a sequential goal completion task, e.g. 1) pick up a key then 2) unlock the door then 3) unlock the treasure chest. A typical machine learning (ML) solution would involve a monolithically trained artificial neural network (ANN). However, if the sequence of goals or the goals themselves change, then the ANN must be significantly (or, at worst, completely) retrained. Instead of a monolithic ANN, a modular ML component would …

This https://arxiv.org/abs/2307.02140 has been replaced.
link: https://scholar.google.com/scholar?q=a

Towards Open Federated Learning Platforms: Survey and Vision from Technical and Legal Perspectives
Traditional Federated Learning (FL) follows a server-dominated cooperation paradigm which narrows the application scenarios of FL and decreases the enthusiasm of data holders to participate. To fully unleash the potential of FL, we advocate rethinking the design of current FL frameworks and extending it to a more generalized concept: Open Federated Learning Platforms, positioned as a crowdsourcing collaborative machine learning infrastructure for all Internet users. We propose two reciprocal co…

Environment-adaptive machine learning potentials
Ngoc Cuong Nguyen, Dionysios Sema
https://arxiv.org/abs/2405.00306 https://arxiv.org…

Environment-adaptive machine learning potentials
The development of interatomic potentials that can effectively capture a wide range of atomic environments is a complex challenge due to several reasons. Materials can exist in numerous structural forms (e.g., crystalline, amorphous, defects, interfaces) and phases (solid, liquid, gas, plasma). Each form may require different treatment in potential modeling to reflect the real physical behavior correctly. Atoms interact through various forces such as electrostatic, van der Waals, ionic bonding,…

Learn the differences between offline and online machine learning, how one can complement the other, and streaming concepts and best practices to start your online ML journey with River, an open source Python ML library, in this short talk by Tun Shwe at this year's Berlin Buzzwords. #bbuzz

This https://arxiv.org/abs/2307.10651 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

Distributional Regression for Data Analysis
Flexible modeling of the entire distribution as a function of covariates is an important generalization of mean-based regression that has seen growing interest over the past decades in both the statistics and machine learning literature. This review outlines selected state-of-the-art statistical approaches to distributional regression, complemented with alternatives from machine learning. Topics covered include the similarities and differences between these approaches, extensions, properties an…

Enhancing Mutual Trustworthiness in Federated Learning for Data-Rich Smart Cities
Osama Wehbi, Sarhad Arisdakessian, Mohsen Guizani, Omar Abdel Wahab, Azzam Mourad, Hadi Otrok, Hoda Al khzaimi, Bassem Ouni
https://arxiv.org/abs/2405.00394

Enhancing Mutual Trustworthiness in Federated Learning for Data-Rich Smart Cities
Federated learning is a promising collaborative and privacy-preserving machine learning approach in data-rich smart cities. Nevertheless, the inherent heterogeneity of these urban environments presents a significant challenge in selecting trustworthy clients for collaborative model training. The usage of traditional approaches, such as the random client selection technique, poses several threats to the system's integrity due to the possibility of malicious client selection. Primarily, the exist…

Distributed Swarm Learning for Edge Internet of Things
Yue Wang, Zhi Tian, FXin Fan, Zhipeng Cai, Cameron Nowzari, Kai Zeng
https://arxiv.org/abs/2403.20188

Distributed Swarm Learning for Edge Internet of Things
The rapid growth of Internet of Things (IoT) has led to the widespread deployment of smart IoT devices at wireless edge for collaborative machine learning tasks, ushering in a new era of edge learning. With a huge number of hardware-constrained IoT devices operating in resource-limited wireless networks, edge learning encounters substantial challenges, including communication and computation bottlenecks, device and data heterogeneity, security risks, privacy leakages, non-convex optimization, a…

This https://arxiv.org/abs/2402.06256 has been replaced.
initial toot: https://mastoxiv.page/@arXi…

Active Sparse Bayesian Committee Machine Potential for Isothermal-Isobaric Molecular Dynamics Simulations
Recent advancements in machine learning potentials (MLPs) have significantly impacted the fields of chemistry, physics, and biology by enabling large-scale first-principles simulations. Among different machine learning approaches, kernel-based MLPs distinguish themselves through their ability to handle small datasets, quantify uncertainties, and minimize over-fitting. Nevertheless, their extensive computational requirements present considerable challenges. To alleviate these, sparsification met…

Quantum AI for Alzheimer's disease early screening
Giacomo Cappiello, Filippo Caruso
https://arxiv.org/abs/2405.00755 https://arx…

Quantum AI for Alzheimer's disease early screening
Quantum machine learning is a new research field combining quantum information science and machine learning. Quantum computing technologies seem to be particularly well suited to solving problems in the health sector in an efficient way, because they may deal with large datasets more efficiently than classical AI. Alzheimer's disease is a neurodegenerative brain disorder that mostly affects elderly people, causing important cognitive impairments. It is the most common cause of dementia and it…

Machine Learning-based Estimation of Respiratory Fluctuations in a Healthy Adult Population using BOLD fMRI and Head Motion Parameters
Abdoljalil Addeh, Fernando Vega, Rebecca J. Williams, G. Bruce Pike, M. Ethan MacDonald
https://arxiv.org/abs/2405.00219

Machine Learning-based Estimation of Respiratory Fluctuations in a Healthy Adult Population using BOLD fMRI and Head Motion Parameters
Motivation: In many fMRI studies, respiratory signals are often missing or of poor quality. Therefore, it could be highly beneficial to have a tool to extract respiratory variation (RV) waveforms directly from fMRI data without the need for peripheral recording devices. Goal(s): Investigate the hypothesis that head motion parameters contain valuable information regarding respiratory patter, which can help machine learning algorithms estimate the RV waveform. Approach: This study proposes a …

This https://arxiv.org/abs/2210.11529 has been replaced.
link: https://scholar.google.com/scholar?q=a

Identifying Lightning Processes in ERA5 Soundings with Deep Learning
Atmospheric environments favorable for lightning and convection are commonly represented by proxies or parameterizations based on expert knowledge such as CAPE, wind shears, charge separation, or combinations thereof. Recent developments in the field of machine learning, high resolution reanalyses, and accurate lightning observations open possibilities for identifying tailored proxies without prior expert knowledge. To identify vertical profiles favorable for lightning, a deep neural network li…

Designing Poisson Integrators Through Machine Learning
Miguel Vaquero, David Mart\'in de Diego, Jorge Cort\'es
https://arxiv.org/abs/2403.20139 htt…

Designing Poisson Integrators Through Machine Learning
This paper presents a general method to construct Poisson integrators, i.e., integrators that preserve the underlying Poisson geometry. We assume the Poisson manifold is integrable, meaning there is a known local symplectic groupoid for which the Poisson manifold serves as the set of units. Our constructions build upon the correspondence between Poisson diffeomorphisms and Lagrangian bisections, which allows us to reformulate the design of Poisson integrators as solutions to a certain PDE (Hami…

Machine Learning for Quantitative MR Image Reconstruction
Andreas Kofler, Felix Frederik Zimmermann, Kostas Papafitsoros
https://arxiv.org/abs/2402.19396 h…

Machine Learning for Quantitative MR Image Reconstruction
In the last years, the design of image reconstruction methods in the field of quantitative Magnetic Resonance Imaging (qMRI) has experienced a paradigm shift. Often, when dealing with (quantitative) MR image reconstruction problems, one is concerned with solving one or a couple of ill-posed inverse problems which require the use of advanced regularization methods. An increasing amount of attention is nowadays put on the development of data-driven methods using Neural Networks (NNs) to learn mea…

This https://arxiv.org/abs/2304.02595 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

Bayesian neural networks via MCMC: a Python-based tutorial
Bayesian inference provides a methodology for parameter estimation and uncertainty quantification in machine learning and deep learning methods. Variational inference and Markov Chain Monte-Carlo (MCMC) sampling methods are used to implement Bayesian inference. In the past three decades, MCMC sampling methods have faced some challenges in being adapted to larger models (such as in deep learning) and big data problems. Advanced proposal distributions that incorporate gradients, such as a Langevi…

Heart Rate and Body Temperature Relationship in Children Admitted to PICU -- A Machine Learning Approach
Emilie Lu, Thanh-Dung Le
https://arxiv.org/abs/2405.00180

Heart Rate and Body Temperature Relationship in Children Admitted to PICU -- A Machine Learning Approach
Vital signs have been essential clinical measures. Among these, body temperature (BT) and heart rate (HR) are particularly significant, and numerous studies explored their association in hospitalized adults and children. However, a lack of in-depth research persists in children admitted to the pediatric intensive care unit (PICU) despite their critical condition requiring particular attention. Objective: In this study, we explore the relationship between HR and BT in children from 0 to 18 years…

Powering In-Database Dynamic Model Slicing for Structured Data Analytics
Lingze Zeng, Naili Xing, Shaofeng Cai, Gang Chen, Beng Chin Ooi, Jian Pei, Yuncheng Wu
https://arxiv.org/abs/2405.00568

Powering In-Database Dynamic Model Slicing for Structured Data Analytics
Relational database management systems (RDBMS) are widely used for the storage and retrieval of structured data. To derive insights beyond statistical aggregation, we typically have to extract specific subdatasets from the database using conventional database operations, and then apply deep neural networks (DNN) training and inference on these respective subdatasets in a separate machine learning system. The process can be prohibitively expensive, especially when there are a combinatorial numbe…

Scale-Robust Timely Asynchronous Decentralized Learning
Purbesh Mitra, Sennur Ulukus
https://arxiv.org/abs/2404.19749 https://arxiv.o…

Scale-Robust Timely Asynchronous Decentralized Learning
We consider an asynchronous decentralized learning system, which consists of a network of connected devices trying to learn a machine learning model without any centralized parameter server. The users in the network have their own local training data, which is used for learning across all the nodes in the network. The learning method consists of two processes, evolving simultaneously without any necessary synchronization. The first process is the model update, where the users update their local…

A neural network-based approach to hybrid systems identification for control
Filippo Fabiani, Bartolomeo Stellato, Daniele Masti, Paul J. Goulart
https://arxiv.org/abs/2404.01814 …

A neural network-based approach to hybrid systems identification for control
We consider the problem of designing a machine learning-based model of an unknown dynamical system from a finite number of (state-input)-successor state data points, such that the model obtained is also suitable for optimal control design. We propose a specific neural network (NN) architecture that yields a hybrid system with piecewise-affine dynamics that is differentiable with respect to the network's parameters, thereby enabling the use of derivative-based training procedures. We show that a…

Thawed Gaussian wavepacket dynamics with $\Delta$-machine learned potentials
Rami Gherib, Ilya G. Ryabinkin, Scott N. Genin
https://arxiv.org/abs/2405.00193

Thawed Gaussian wavepacket dynamics with $Δ$-machine learned potentials
A method for performing variable-width (thawed) Gaussian wavepacket (GWP) variational dynamics on machine-learned potentials is presented. Instead of fitting the potential energy surface (PES), the anharmonic correction to the global harmonic approximation (GHA) is fitted using kernel ridge regression -- this is a $Δ$-machine learning approach. The training set consists of energy differences between ab initio electronic energies and values given by the GHA. The learned potential is subsequentl…

This https://arxiv.org/abs/2404.02595 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qu…

QFNN-FFD: Quantum Federated Neural Network for Financial Fraud Detection
This study introduces the Quantum Federated Neural Network for Financial Fraud Detection (QFNN-FFD), a cutting-edge framework merging Quantum Machine Learning (QML) and quantum computing with Federated Learning (FL) for financial fraud detection. Using quantum technologies' computational power and the robust data privacy protections offered by FL, QFNN-FFD emerges as a secure and efficient method for identifying fraudulent transactions within the financial sector. Implementing a dual-phase trai…

Swarm Learning: A Survey of Concepts, Applications, and Trends
Elham Shammar, Xiaohui Cui, Mohammed A. A. Al-qaness
https://arxiv.org/abs/2405.00556 https:…

Swarm Learning: A Survey of Concepts, Applications, and Trends
Deep learning models have raised privacy and security concerns due to their reliance on large datasets on central servers. As the number of Internet of Things (IoT) devices increases, artificial intelligence (AI) will be crucial for resource management, data processing, and knowledge acquisition. To address those issues, federated learning (FL) has introduced a novel approach to building a versatile, large-scale machine learning framework that operates in a decentralized and hardware-agnostic m…

This https://arxiv.org/abs/2304.07682 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_hepp…

Analysis of strong coupling constant with machine learning and its application
In this work, we investigate the nature of the strong coupling constant and related physics. Through the analysis of accumulated experimental data from around the world, we employ the ability of machine learning to unravel its physical laws. The result of our efforts is a formula that captures the expansive panorama of the distribution of the strong coupling constant across the entire energy range. Importantly, this newly derived expression is very similar to the formula derived from the Dyson-…

This https://arxiv.org/abs/2401.10375 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

Vulnerabilities of Foundation Model Integrated Federated Learning Under Adversarial Threats
Federated Learning (FL) addresses critical issues in machine learning related to data privacy and security, yet suffering from data insufficiency and imbalance under certain circumstances. The emergence of foundation models (FMs) offers potential solutions to the limitations of existing FL frameworks, e.g., by generating synthetic data for model initialization. However, due to the inherent safety concerns of FMs, integrating FMs into FL could introduce new risks, which remains largely unexplore…

Swarm Learning: A Survey of Concepts, Applications, and Trends
Elham Shammar, Xiaohui Cui, Mohammed A. A. Al-qaness
https://arxiv.org/abs/2405.00556 https:…

Swarm Learning: A Survey of Concepts, Applications, and Trends
Deep learning models have raised privacy and security concerns due to their reliance on large datasets on central servers. As the number of Internet of Things (IoT) devices increases, artificial intelligence (AI) will be crucial for resource management, data processing, and knowledge acquisition. To address those issues, federated learning (FL) has introduced a novel approach to building a versatile, large-scale machine learning framework that operates in a decentralized and hardware-agnostic m…

Modular, Hierarchical Machine Learning for Sequential Goal Completion
Nathan McDonald
https://arxiv.org/abs/2404.19060 https://arxiv.…

Modular, Hierarchical Machine Learning for Sequential Goal Completion
Given a maze populated with different objects, one may task a robot with a sequential goal completion task, e.g. 1) pick up a key then 2) unlock the door then 3) unlock the treasure chest. A typical machine learning (ML) solution would involve a monolithically trained artificial neural network (ANN). However, if the sequence of goals or the goals themselves change, then the ANN must be significantly (or, at worst, completely) retrained. Instead of a monolithic ANN, a modular ML component would …

HLSTransform: Energy-Efficient Llama 2 Inference on FPGAs Via High Level Synthesis
Andy He, Darren Key, Mason Bulling, Andrew Chang, Skyler Shapiro, Everett Lee
https://arxiv.org/abs/2405.00738

HLSTransform: Energy-Efficient Llama 2 Inference on FPGAs Via High Level Synthesis
Graphics Processing Units (GPUs) have become the leading hardware accelerator for deep learning applications and are used widely in training and inference of transformers; transformers have achieved state-of-the-art performance in many areas of machine learning and are especially used in most modern Large Language Models (LLMs). However, GPUs require large amounts of energy, which poses environmental concerns, demands high operational costs, and causes GPUs to be unsuitable for edge computing. …

Constraining the giant radio galaxy population with machine learning and Bayesian inference
Rafa\"el I. J. Mostert, Martijn S. S. L. Oei, B. Barkus, Lara Alegre, Martin J. Hardcastle, Kenneth J. Duncan, Huub J. A. R\"ottgering, Reinout J. van Weeren, Maya Horton
https://arxiv.org/abs/2405.00232

Constraining the giant radio galaxy population with machine learning and Bayesian inference
Large-scale sky surveys at low frequencies, like the LOFAR Two-metre Sky Survey (LoTSS), allow for the detection and characterisation of unprecedented numbers of giant radio galaxies (GRGs, or 'giants'). In this work, by automating the creation of radio--optical catalogues, we aim to significantly expand the census of known giants. We then combine this sample with a forward model to constrain GRG properties of cosmological interest. In particular, we automate radio source component association …

Automatic Cardiac Pathology Recognition in Echocardiography Images Using Higher Order Dynamic Mode Decomposition and a Vision Transformer for Small Datasets
Andr\'es Bell-Navas, Nourelhouda Groun, Mar\'ia Villalba-Orero, Enrique Lara-Pezzi, Jes\'us Garicano-Mena, Soledad Le Clainche
https://arxiv.org/abs/2404.19579 https://arxiv.org/pdf/2404.19579
arXiv:2404.19579v1 Announce Type: new
Abstract: Heart diseases are the main international cause of human defunction. According to the WHO, nearly 18 million people decease each year because of heart diseases. Also considering the increase of medical data, much pressure is put on the health industry to develop systems for early and accurate heart disease recognition. In this work, an automatic cardiac pathology recognition system based on a novel deep learning framework is proposed, which analyses in real-time echocardiography video sequences. The system works in two stages. The first one transforms the data included in a database of echocardiography sequences into a machine-learning-compatible collection of annotated images which can be used in the training stage of any kind of machine learning-based framework, and more specifically with deep learning. This includes the use of the Higher Order Dynamic Mode Decomposition (HODMD) algorithm, for the first time to the authors' knowledge, for both data augmentation and feature extraction in the medical field. The second stage is focused on building and training a Vision Transformer (ViT), barely explored in the related literature. The ViT is adapted for an effective training from scratch, even with small datasets. The designed neural network analyses images from an echocardiography sequence to predict the heart state. The results obtained show the superiority of the proposed system and the efficacy of the HODMD algorithm, even outperforming pretrained Convolutional Neural Networks (CNNs), which are so far the method of choice in the literature.

This https://arxiv.org/abs/2303.07230 has been replaced.
link: https://scholar.google.com/scholar?q=a

Systematic Evaluation of Deep Learning Models for Failure Prediction
With the increasing complexity and scope of software systems, their dependability is crucial. The analysis of log data recorded during system execution can enable engineers to automatically predict failures at run time. Several Machine Learning (ML) techniques, including traditional ML and Deep Learning (DL), have been proposed to automate such tasks. However, current empirical studies are limited in terms of covering all main DL types -- Recurrent Neural Network (RNN), Convolutional Neural net…

This https://arxiv.org/abs/2401.10375 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

Vulnerabilities of Foundation Model Integrated Federated Learning Under Adversarial Threats
Federated Learning (FL) addresses critical issues in machine learning related to data privacy and security, yet suffering from data insufficiency and imbalance under certain circumstances. The emergence of foundation models (FMs) offers potential solutions to the limitations of existing FL frameworks, e.g., by generating synthetic data for model initialization. However, due to the inherent safety concerns of FMs, integrating FMs into FL could introduce new risks, which remains largely unexplore…

This https://arxiv.org/abs/2304.05301 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDC_…

TACOS: Topology-Aware Collective Algorithm Synthesizer for Distributed Machine Learning
The surge of artificial intelligence, specifically large language models, has led to a rapid advent towards the development of large-scale machine learning training clusters. Collective communications within these clusters tend to be heavily bandwidth-bound, necessitating techniques to optimally utilize the available network bandwidth. This puts the routing algorithm for the collective at the forefront of determining the performance. Unfortunately, communication libraries used in distributed ma…

Leveraging Diverse Modeling Contexts with Collaborating Learning for Neural Machine Translation
Yusheng Liao, Yanfeng Wang, Yu Wang
https://arxiv.org/abs/2402.18428

Leveraging Diverse Modeling Contexts with Collaborating Learning for Neural Machine Translation
Autoregressive (AR) and Non-autoregressive (NAR) models are two types of generative models for Neural Machine Translation (NMT). AR models predict tokens in a word-by-word manner and can effectively capture the distribution of real translations. NAR models predict tokens by extracting bidirectional contextual information which can improve the inference speed but they suffer from performance degradation. Previous works utilized AR models to enhance NAR models by reducing the training data's comp…

Functional Bilevel Optimization for Machine Learning
Ieva Petrulionyte, Julien Mairal, Michael Arbel
https://arxiv.org/abs/2403.20233 https://

Functional Bilevel Optimization for Machine Learning
In this paper, we introduce a new functional point of view on bilevel optimization problems for machine learning, where the inner objective is minimized over a function space. These types of problems are most often solved by using methods developed in the parametric setting, where the inner objective is strongly convex with respect to the parameters of the prediction function. The functional point of view does not rely on this assumption and notably allows using over-parameterized neural networ…

Active Learning with Task Adaptation Pre-training for Speech Emotion Recognition
Dongyuan Li, Ying Zhang, Yusong Wang, Funakoshi Kataro, Manabu Okumura
https://arxiv.org/abs/2405.00307

Active Learning with Task Adaptation Pre-training for Speech Emotion Recognition
Speech emotion recognition (SER) has garnered increasing attention due to its wide range of applications in various fields, including human-machine interaction, virtual assistants, and mental health assistance. However, existing SER methods often overlook the information gap between the pre-training speech recognition task and the downstream SER task, resulting in sub-optimal performance. Moreover, current methods require much time for fine-tuning on each specific speech dataset, such as IEMOCA…

Designing Poisson Integrators Through Machine Learning
Miguel Vaquero, David Mart\'in de Diego, Jorge Cort\'es
https://arxiv.org/abs/2403.20139 htt…

Designing Poisson Integrators Through Machine Learning
This paper presents a general method to construct Poisson integrators, i.e., integrators that preserve the underlying Poisson geometry. We assume the Poisson manifold is integrable, meaning there is a known local symplectic groupoid for which the Poisson manifold serves as the set of units. Our constructions build upon the correspondence between Poisson diffeomorphisms and Lagrangian bisections, which allows us to reformulate the design of Poisson integrators as solutions to a certain PDE (Hami…

Three-layer deep learning network random trees for fault diagnosis in chemical production process
Ming Lu, Zhen Gao, Ying Zou, Zuguo Chen, Pei Li
https://arxiv.org/abs/2405.00311 …

Three-layer deep learning network random trees for fault diagnosis in chemical production process
With the development of technology, the chemical production process is becoming increasingly complex and large-scale, making fault diagnosis particularly important. However, current diagnostic methods struggle to address the complexities of large-scale production processes. In this paper, we integrate the strengths of deep learning and machine learning technologies, combining the advantages of bidirectional long and short-term memory neural networks, fully connected neural networks, and the ext…

Machine Learning for Quantum Computing Specialists
Daniel Goldsmith, M M Hassan Mahmud
https://arxiv.org/abs/2404.18555 https://arxiv…

Machine Learning for Quantum Computing Specialists
Quantum machine learning (QML) is a promising early use case for quantum computing. There has been progress in the last five years from theoretical studies and numerical simulations to proof of concepts. Use cases demonstrated on contemporary quantum devices include classifying medical images and items from the Iris dataset, classifying and generating handwritten images, toxicity screening, and learning a probability distribution. Potential benefits of QML include faster training and identifica…

Na Vacancy Driven Phase Transformation and Fast Ion Conduction in W-doped Na$_3$SbS$_4$ from Machine Learning Force Fields
Johan Klarbring, Aron Walsh
https://arxiv.org/abs/2403.20138

Na Vacancy Driven Phase Transformation and Fast Ion Conduction in W-doped Na$_3$SbS$_4$ from Machine Learning Force Fields
Solid-state sodium batteries require effective electrolytes that conduct at room temperature. The Na$_3$SbS$_4$ (Pn = P, Sb; Ch = S, Se) family have been studied for their high Na ion conductivity. The population of Na vacancies, which mediate ion diffusion in these materials, can be enhanced through aliovalent doping on the pnictogen site. To probe the microscopic role of extrinsic doping, and its impact on diffusion and phase stability, we trained a machine learning force field for Na$_{3-x}$…

Thawed Gaussian wavepacket dynamics with $\Delta$-machine learned potentials
Rami Gherib, Ilya G. Ryabinkin, Scott N. Genin
https://arxiv.org/abs/2405.00193

Thawed Gaussian wavepacket dynamics with $Δ$-machine learned potentials
A method for performing variable-width (thawed) Gaussian wavepacket (GWP) variational dynamics on machine-learned potentials is presented. Instead of fitting the potential energy surface (PES), the anharmonic correction to the global harmonic approximation (GHA) is fitted using kernel ridge regression -- this is a $Δ$-machine learning approach. The training set consists of energy differences between ab initio electronic energies and values given by the GHA. The learned potential is subsequentl…

Three-layer deep learning network random trees for fault diagnosis in chemical production process
Ming Lu, Zhen Gao, Ying Zou, Zuguo Chen, Pei Li
https://arxiv.org/abs/2405.00311 …

Three-layer deep learning network random trees for fault diagnosis in chemical production process
With the development of technology, the chemical production process is becoming increasingly complex and large-scale, making fault diagnosis particularly important. However, current diagnostic methods struggle to address the complexities of large-scale production processes. In this paper, we integrate the strengths of deep learning and machine learning technologies, combining the advantages of bidirectional long and short-term memory neural networks, fully connected neural networks, and the ext…

Accelerating Computer Architecture Simulation through Machine Learning
Wajid Ali, Ayaz Akram
https://arxiv.org/abs/2402.18746 https://

Accelerating Computer Architecture Simulation through Machine Learning
This paper presents our approach to accelerate computer architecture simulation by leveraging machine learning techniques. Traditional computer architecture simulations are time-consuming, making it challenging to explore different design choices efficiently. Our proposed model utilizes a combination of application features and micro-architectural features to predict the performance of an application. These features are derived from simulations of a small portion of the application. We demonstr…

This https://arxiv.org/abs/2310.09690 has been replaced.
link: https://scholar.google.com/scholar?q=a

Configuration Validation with Large Language Models
Misconfigurations are major causes of software failures. Existing practices rely on developer-written rules or test cases to validate configurations, which are expensive. Machine learning (ML) for configuration validation is considered a promising direction, but has been facing challenges such as the need of large-scale field data and system-specific models. Recent advances in Large Language Models (LLMs) show promise in addressing some of the long-lasting limitations of ML-based configuration …

This https://arxiv.org/abs/2103.09603 has been replaced.
link: https://scholar.google.com/scholar?q=a

DoubleML -- An Object-Oriented Implementation of Double Machine Learning in R
The R package DoubleML implements the double/debiased machine learning framework of Chernozhukov et al. (2018). It provides functionalities to estimate parameters in causal models based on machine learning methods. The double machine learning framework consist of three key ingredients: Neyman orthogonality, high-quality machine learning estimation and sample splitting. Estimation of nuisance components can be performed by various state-of-the-art machine learning methods that are available in t…

Voice Signal Processing for Machine Learning. The Case of Speaker Isolation
Radan Ganchev
https://arxiv.org/abs/2403.20202 https://ar…

Voice Signal Processing for Machine Learning. The Case of Speaker Isolation
The widespread use of automated voice assistants along with other recent technological developments have increased the demand for applications that process audio signals and human voice in particular. Voice recognition tasks are typically performed using artificial intelligence and machine learning models. Even though end-to-end models exist, properly pre-processing the signal can greatly reduce the complexity of the task and allow it to be solved with a simpler ML model and fewer computational…

This https://arxiv.org/abs/2308.13096 has been replaced.
initial toot: https://mastoxiv.page/@a…

Electronic Structure Prediction of Multi-million Atom Systems Through Uncertainty Quantification Enabled Transfer Learning
The ground state electron density -- obtainable using Kohn-Sham Density Functional Theory (KS-DFT) simulations -- contains a wealth of material information, making its prediction via machine learning (ML) models attractive. However, the computational expense of KS-DFT scales cubically with system size which tends to stymie training data generation, making it difficult to develop quantifiably accurate ML models that are applicable across many scales and system configurations. Here, we address th…

A Methodology for Improving Accuracy of Embedded Spiking Neural Networks through Kernel Size Scaling
Rachmad Vidya Wicaksana Putra, Muhammad Shafique
https://arxiv.org/abs/2404.01685

A Methodology for Improving Accuracy of Embedded Spiking Neural Networks through Kernel Size Scaling
Spiking Neural Networks (SNNs) can offer ultra low power/ energy consumption for machine learning-based applications due to their sparse spike-based operations. Currently, most of the SNN architectures need a significantly larger model size to achieve higher accuracy, which is not suitable for resource-constrained embedded applications. Therefore, developing SNNs that can achieve high accuracy with acceptable memory footprint is highly needed. Toward this, we propose a novel methodology that im…

This https://arxiv.org/abs/2103.09603 has been replaced.
link: https://scholar.google.com/scholar?q=a

DoubleML -- An Object-Oriented Implementation of Double Machine Learning in R
The R package DoubleML implements the double/debiased machine learning framework of Chernozhukov et al. (2018). It provides functionalities to estimate parameters in causal models based on machine learning methods. The double machine learning framework consist of three key ingredients: Neyman orthogonality, high-quality machine learning estimation and sample splitting. Estimation of nuisance components can be performed by various state-of-the-art machine learning methods that are available in t…

Machine learning for modular multiplication
Kristin Lauter, Cathy Yuanchen Li, Krystal Maughan, Rachel Newton, Megha Srivastava
https://arxiv.org/abs/2402.19254

Machine learning for modular multiplication
Motivated by cryptographic applications, we investigate two machine learning approaches to modular multiplication: namely circular regression and a sequence-to-sequence transformer model. The limited success of both methods demonstrated in our results gives evidence for the hardness of tasks involving modular multiplication upon which cryptosystems are based.

Quantum-enhanced learning with a controllable bosonic variational sensor network
Pengcheng Liao, Bingzhi Zhang, Quntao Zhuang
https://arxiv.org/abs/2404.18293

Quantum-enhanced learning with a controllable bosonic variational sensor network
The emergence of quantum sensor networks has presented opportunities for enhancing complex sensing tasks, while simultaneously introducing significant challenges in designing and analyzing quantum sensing protocols due to the intricate nature of entanglement and physical processes. Supervised learning assisted by an entangled sensor network (SLAEN) [Phys. Rev. X 9, 041023 (2019)] represents a promising paradigm for automating sensor-network design through variational quantum machine learning. H…

State-of-the-Art Approaches to Enhancing Privacy Preservation of Machine Learning Datasets: A Survey
Chaoyu Zhang
https://arxiv.org/abs/2404.16847 https://…

State-of-the-Art Approaches to Enhancing Privacy Preservation of Machine Learning Datasets: A Survey
This paper examines the evolving landscape of machine learning (ML) and its profound impact across various sectors, with a special focus on the emerging field of Privacy-preserving Machine Learning (PPML). As ML applications become increasingly integral to industries like telecommunications, financial technology, and surveillance, they raise significant privacy concerns, necessitating the development of PPML strategies. The paper highlights the unique challenges in safeguarding privacy within M…

Hardware Accelerators for Autonomous Cars: A Review
Ruba Islayem, Fatima Alhosani, Raghad Hashem, Afra Alzaabi, Mahmoud Meribout
https://arxiv.org/abs/2405.00062

Hardware Accelerators for Autonomous Cars: A Review
Autonomous Vehicles (AVs) redefine transportation with sophisticated technology, integrating sensors, cameras, and intricate algorithms. Implementing machine learning in AV perception demands robust hardware accelerators to achieve real-time performance at reasonable power consumption and footprint. Lot of research and development efforts using different technologies are still being conducted to achieve the goal of getting a fully AV and some cars manufactures offer commercially available syste…

This https://arxiv.org/abs/2402.10931 has been replaced.
initial toot: https://mastoxiv.page/@a…

Enabling discovery of materials through enhanced generalisability of deep learning models
The road towards the discovery of new, useful materials is full of imperfections. Machine learning, which is currently the power horse of material discovery when it works in concert with density functional theory, has been able to accelerate the discovery of new materials for various applications by learning the properties of known, stable materials to infer the properties of unknown, deformed materials. Physics-informed machine learning (PIML) is particularly believed to bridge the gap between…

Investigating Gender Fairness in Machine Learning-driven Personalized Care for Chronic Pain
Pratik Gajane, Sean Newman, John D. Piette
https://arxiv.org/abs/2402.19226

Investigating Gender Fairness in Machine Learning-driven Personalized Care for Chronic Pain
This study investigates gender fairness in personalized pain care recommendations using machine learning algorithms. Leveraging a contextual bandits framework, personalized recommendations are formulated and evaluated using LinUCB algorithm on a dataset comprising interactions with $164$ patients across $10$ sessions each. Results indicate that while adjustments to algorithm parameters influence the quality of pain care recommendations, this impact remains consistent across genders. However, wh…

[2024-05-02 Thu (UTC), 4 new articles found for stat.ML Machine Learning]

This https://arxiv.org/abs/2404.16156 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qu…

Guardians of the Quantum GAN
Quantum Generative Adversarial Networks (qGANs) are at the forefront of image-generating quantum machine learning models. To accommodate the growing demand for Noisy Intermediate-Scale Quantum (NISQ) devices to train and infer quantum machine learning models, the number of third-party vendors offering quantum hardware as a service is expected to rise. This expansion introduces the risk of untrusted vendors potentially stealing proprietary information from the quantum machine learning models. To…

AAA: an Adaptive Mechanism for Locally Differential Private Mean Estimation
Fei Wei, Ergute Bao, Xiaokui Xiao, Yin Yang, Bolin Ding
https://arxiv.org/abs/2404.01625

AAA: an Adaptive Mechanism for Locally Differential Private Mean Estimation
Local differential privacy (LDP) is a strong privacy standard that has been adopted by popular software systems. The main idea is that each individual perturbs their own data locally, and only submits the resulting noisy version to a data aggregator. Although much effort has been devoted to computing various types of aggregates and building machine learning applications under LDP, research on fundamental perturbation mechanisms has not achieved significant improvement in recent years. Towards a…

[2024-04-02 Tue (UTC), no new articles found for stat.ML Machine Learning]

Belt and Brace: When Federated Learning Meets Differential Privacy
Xuebin Ren, Shusen Yang, Cong Zhao, Julie McCann, Zongben Xu
https://arxiv.org/abs/2404.18814

Belt and Brace: When Federated Learning Meets Differential Privacy
Federated learning (FL) has great potential for large-scale machine learning (ML) without exposing raw data.Differential privacy (DP) is the de facto standard of privacy protection with provable guarantees.Advances in ML suggest that DP would be a perfect fit for FL with comprehensive privacy preservation. Hence, extensive efforts have been devoted to achieving practically usable FL with DP, which however is still challenging.Practitioners often not only are not fully aware of its development a…

[2024-04-02 Tue (UTC), no new articles found for cs.LG Machine Learning]

Geometric Insights into Focal Loss: Reducing Curvature for Enhanced Model Calibration
Masanari Kimura, Hiroki Naganuma
https://arxiv.org/abs/2405.00442 htt…

Geometric Insights into Focal Loss: Reducing Curvature for Enhanced Model Calibration
The key factor in implementing machine learning algorithms in decision-making situations is not only the accuracy of the model but also its confidence level. The confidence level of a model in a classification problem is often given by the output vector of a softmax function for convenience. However, these values are known to deviate significantly from the actual expected model confidence. This problem is called model calibration and has been studied extensively. One of the simplest techniques …

On the Relevance of Byzantine Robust Optimization Against Data Poisoning
Sadegh Farhadkhani, Rachid Guerraoui, Nirupam Gupta, Rafael Pinot
https://arxiv.org/abs/2405.00491

On the Relevance of Byzantine Robust Optimization Against Data Poisoning
The success of machine learning (ML) has been intimately linked with the availability of large amounts of data, typically collected from heterogeneous sources and processed on vast networks of computing devices (also called {\em workers}). Beyond accuracy, the use of ML in critical domains such as healthcare and autonomous driving calls for robustness against {\em data poisoning}and some {\em faulty workers}. The problem of {\em Byzantine ML} formalizes these robustness issues by considering a …

On the Relevance of Byzantine Robust Optimization Against Data Poisoning
Sadegh Farhadkhani, Rachid Guerraoui, Nirupam Gupta, Rafael Pinot
https://arxiv.org/abs/2405.00491

On the Relevance of Byzantine Robust Optimization Against Data Poisoning
The success of machine learning (ML) has been intimately linked with the availability of large amounts of data, typically collected from heterogeneous sources and processed on vast networks of computing devices (also called {\em workers}). Beyond accuracy, the use of ML in critical domains such as healthcare and autonomous driving calls for robustness against {\em data poisoning}and some {\em faulty workers}. The problem of {\em Byzantine ML} formalizes these robustness issues by considering a …

When does Subagging Work?
Christos Revelas, Otilia Boldea, Bas J. M. Werker
https://arxiv.org/abs/2404.01832 https://arxiv.org/pdf/24…

When does Subagging Work?
We study the effectiveness of subagging, or subsample aggregating, on regression trees, a popular non-parametric method in machine learning. First, we give sufficient conditions for pointwise consistency of trees. We formalize that (i) the bias depends on the diameter of cells, hence trees with few splits tend to be biased, and (ii) the variance depends on the number of observations in cells, hence trees with many splits tend to have large variance. While these statements for bias and variance …

Evaluations of Machine Learning Privacy Defenses are Misleading
Michael Aerni, Jie Zhang, Florian Tram\`er
https://arxiv.org/abs/2404.17399 https://…

Evaluations of Machine Learning Privacy Defenses are Misleading
Empirical defenses for machine learning privacy forgo the provable guarantees of differential privacy in the hope of achieving higher utility while resisting realistic adversaries. We identify severe pitfalls in existing empirical privacy evaluations (based on membership inference attacks) that result in misleading conclusions. In particular, we show that prior evaluations fail to characterize the privacy leakage of the most vulnerable samples, use weak attacks, and avoid comparisons with pract…

M-DEW: Extending Dynamic Ensemble Weighting to Handle Missing Values
Adam Catto, Nan Jia, Ansaf Salleb-Aouissi, Anita Raja
https://arxiv.org/abs/2405.00182

M-DEW: Extending Dynamic Ensemble Weighting to Handle Missing Values
Missing value imputation is a crucial preprocessing step for many machine learning problems. However, it is often considered as a separate subtask from downstream applications such as classification, regression, or clustering, and thus is not optimized together with them. We hypothesize that treating the imputation model and downstream task model together and optimizing over full pipelines will yield better results than treating them separately. Our work describes a novel AutoML technique for m…

Variational Bayesian Methods for a Tree-Structured Stick-Breaking Process Mixture of Gaussians
Yuta Nakahara
https://arxiv.org/abs/2405.00385 https://

Variational Bayesian Methods for a Tree-Structured Stick-Breaking Process Mixture of Gaussians
The Bayes coding algorithm for context tree source is a successful example of Bayesian tree estimation in text compression in information theory. This algorithm provides an efficient parametric representation of the posterior tree distribution and exact updating of its parameters. We apply this algorithm to a clustering task in machine learning. More specifically, we apply it to Bayesian estimation of the tree-structured stick-breaking process (TS-SBP) mixture models. For TS-SBP mixture models,…

M-DEW: Extending Dynamic Ensemble Weighting to Handle Missing Values
Adam Catto, Nan Jia, Ansaf Salleb-Aouissi, Anita Raja
https://arxiv.org/abs/2405.00182

M-DEW: Extending Dynamic Ensemble Weighting to Handle Missing Values
Missing value imputation is a crucial preprocessing step for many machine learning problems. However, it is often considered as a separate subtask from downstream applications such as classification, regression, or clustering, and thus is not optimized together with them. We hypothesize that treating the imputation model and downstream task model together and optimizing over full pipelines will yield better results than treating them separately. Our work describes a novel AutoML technique for m…

DIGIC: Domain Generalizable Imitation Learning by Causal Discovery
Yang Chen, Yitao Liang, Zhouchen Lin
https://arxiv.org/abs/2402.18910 https://

DIGIC: Domain Generalizable Imitation Learning by Causal Discovery
Causality has been combined with machine learning to produce robust representations for domain generalization. Most existing methods of this type require massive data from multiple domains to identify causal features by cross-domain variations, which can be expensive or even infeasible and may lead to misidentification in some cases. In this work, we make a different attempt by leveraging the demonstration data distribution to discover the causal features for a domain generalizable policy. We d…

This https://arxiv.org/abs/2403.19871 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Towards Stable Machine Learning Model Retraining via Slowly Varying Sequences
Retraining machine learning models (ML) when new batches of data become available is an important task in real-world pipelines. Existing methods focus largely on greedy approaches to find the best-performing model for each batch, without considering the stability of the model's structure across retraining iterations. In this study, we propose a methodology for finding sequences of ML models that are stable across retraining iterations. We develop a mixed-integer optimization algorithm that is g…