Tootfinder

Homogenization of Multi-agent Learning Dynamics in Finite-state Markov Games
Yann Kerzreho (ENS Paris Saclay)
https://arxiv.org/abs/2506.21079 https://

Homogenization of Multi-agent Learning Dynamics in Finite-state Markov Games
This paper introduces a new approach for approximating the learning dynamics of multiple reinforcement learning (RL) agents interacting in a finite-state Markov game. The idea is to rescale the learning process by simultaneously reducing the learning rate and increasing the update frequency, effectively treating the agent's parameters as a slow-evolving variable influenced by the fast-mixing game state. Under mild assumptions-ergodicity of the state process and continuity of the updates-we prov…

CultureMERT: Continual Pre-Training for Cross-Cultural Music Representation Learning
Angelos-Nikolaos Kanatas, Charilaos Papaioannou, Alexandros Potamianos
https://arxiv.org/abs/2506.17818

CultureMERT: Continual Pre-Training for Cross-Cultural Music Representation Learning
Recent advances in music foundation models have improved audio representation learning, yet their effectiveness across diverse musical traditions remains limited. We introduce CultureMERT-95M, a multi-culturally adapted foundation model developed to enhance cross-cultural music representation learning and understanding. To achieve this, we propose a two-stage continual pre-training strategy that integrates learning rate re-warming and re-decaying, enabling stable adaptation even with limited co…

Bayesian inference for the learning rate in Generalised Bayesian inference
Jeong Eun Lee, Sitong Liu, Geoff K. Nicholls
https://arxiv.org/abs/2506.12532 ht…

Bayesian inference for the learning rate in Generalised Bayesian inference
In Generalised Bayesian Inference (GBI), the learning rate and hyperparameters of the loss must be estimated. However, these inference-hyperparameters can't be estimated jointly with the other parameters by giving them a prior, as we discuss. Several methods for estimating the learning rate have been given which elicit and minimise a loss based on the goals of the overall inference (in our case, prediction of new data). However, in some settings there exists an unknown ``true'' learning rate ab…

End-to-End Learning of Probabilistic Constellation Shaping through Importance Sampling
Shrinivas Chimmalgi, Laurent Schmalen, Vahid Aref
https://arxiv.org/abs/2506.16098

End-to-End Learning of Probabilistic Constellation Shaping through Importance Sampling
Probabilistic constellation shaping enables easy rate adaption and has been proven to reduce the gap to Shannon capacity. Constellation point probabilities are optimized to maximize either the mutual information or the bit-wise mutual information. The optimization problem is however challenging even for simple channel models. While autoencoder-based machine learning has been applied successfully to solve this problem [1], it requires manual computation of additional terms for the gradient which…

Few-Shot Learning-Based Cyber Incident Detection with Augmented Context Intelligence
Fei Zuo, Junghwan Rhee, Yung Ryn Choe, Chenglong Fu, Xianshan Qu
https://arxiv.org/abs/2506.16626

Few-Shot Learning-Based Cyber Incident Detection with Augmented Context Intelligence
In recent years, the adoption of cloud services has been expanding at an unprecedented rate. As more and more organizations migrate or deploy their businesses to the cloud, a multitude of related cybersecurity incidents such as data breaches are on the rise. Many inherent attributes of cloud environments, for example, data sharing, remote access, dynamicity and scalability, pose significant challenges for the protection of cloud security. Even worse, cyber threats are becoming increasingly soph…

Integrating Radiomics with Deep Learning Enhances Multiple Sclerosis Lesion Delineation
Nadezhda Alsahanova, Pavel Bartenev, Maksim Sharaev, Milos Ljubisavljevic, Taleb Al. Mansoori, Yauhen Statsenko
https://arxiv.org/abs/2506.14524

Integrating Radiomics with Deep Learning Enhances Multiple Sclerosis Lesion Delineation
Background: Accurate lesion segmentation is critical for multiple sclerosis (MS) diagnosis, yet current deep learning approaches face robustness challenges. Aim: This study improves MS lesion segmentation by combining data fusion and deep learning techniques. Materials and Methods: We suggested novel radiomic features (concentration rate and Rényi entropy) to characterize different MS lesion types and fused these with raw imaging data. The study integrated radiomic features with imaging da…

Efficient Beam Selection for ISAC in Cell-Free Massive MIMO via Digital Twin-Assisted Deep Reinforcement Learning
Jiexin Zhang, Shu Xu, Chunguo Li, Yongming Huang, Luxi Yang
https://arxiv.org/abs/2506.18560

Efficient Beam Selection for ISAC in Cell-Free Massive MIMO via Digital Twin-Assisted Deep Reinforcement Learning
Beamforming enhances signal strength and quality by focusing energy in specific directions. This capability is particularly crucial in cell-free integrated sensing and communication (ISAC) systems, where multiple distributed access points (APs) collaborate to provide both communication and sensing services. In this work, we first derive the distribution of joint target detection probabilities across multiple receiving APs under false alarm rate constraints, and then formulate the beam selection…

A Gradient Meta-Learning Joint Optimization for Beamforming and Antenna Position in Pinching-Antenna Systems
Kang Zhou, Weixi Zhou, Donghong Cai, Xianfu Lei, Yanqing Xu, Zhiguo Ding, Pingzhi Fan
https://arxiv.org/abs/2506.12583

A Gradient Meta-Learning Joint Optimization for Beamforming and Antenna Position in Pinching-Antenna Systems
In this paper, we consider a novel optimization design for multi-waveguide pinching-antenna systems, aiming to maximize the weighted sum rate (WSR) by jointly optimizing beamforming coefficients and antenna position. To handle the formulated non-convex problem, a gradient-based meta-learning joint optimization (GML-JO) algorithm is proposed. Specifically, the original problem is initially decomposed into two sub-problems of beamforming optimization and antenna position optimization through equi…

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…

Generalised Rate Control Approach For Stream Processing Applications
Ziren Xiao
https://arxiv.org/abs/2506.11710 https://arxiv.org/pd…

Generalised Rate Control Approach For Stream Processing Applications
Distributed stream processing systems are widely deployed to process real-time data generated by various devices, such as sensors and software systems. A key challenge in the system is overloading, which leads to an unstable system status and consumes additional system resources. In this paper, we use a graph neural network-based deep reinforcement learning to collaboratively control the data emission rate at which the data is generated in the stream source to proactively avoid overloading scen…

Deep reinforcement learning for near-deterministic preparation of cubic- and quartic-phase gates in photonic quantum computing
Amanuel Anteneh L\'eandre Brunel, Carlos Gonz\'alez-Arciniegas, Olivier Pfister
https://arxiv.org/abs/2506.07859

Deep reinforcement learning for near-deterministic preparation of cubic- and quartic-phase gates in photonic quantum computing
Cubic-phase states are a sufficient resource for universal quantum computing over continuous variables. We present results from numerical experiments in which deep neural networks are trained via reinforcement learning to control a quantum optical circuit for generating cubic-phase states, with an average success rate of 96%. The only non-Gaussian resource required is photon-number-resolving measurements. We also show that the exact same resources enable the direct generation of a quartic-phase…

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…

This https://arxiv.org/abs/2503.20117 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainable
This work tackles the fundamental challenges in Federated Learning (FL) posed by arbitrary client participation and data heterogeneity, prevalent characteristics in practical FL settings. It is well-established that popular FedAvg-style algorithms struggle with exact convergence and can suffer from slow convergence rates since a decaying learning rate is required to mitigate these scenarios. To address these issues, we introduce the concept of stochastic matrix and the corresponding time-varyin…

ABC: Adaptive BayesNet Structure Learning for Computational Scalable Multi-task Image Compression
Yufeng Zhang, Wenrui Dai, Hang Yu, Shizhan Liu, Junhui Hou, Jianguo Li, Weiyao Lin
https://arxiv.org/abs/2506.15228

ABC: Adaptive BayesNet Structure Learning for Computational Scalable Multi-task Image Compression
Neural Image Compression (NIC) has revolutionized image compression with its superior rate-distortion performance and multi-task capabilities, supporting both human visual perception and machine vision tasks. However, its widespread adoption is hindered by substantial computational demands. While existing approaches attempt to address this challenge through module-specific optimizations or pre-defined complexity levels, they lack comprehensive control over computational complexity. We present A…

GEARS H: Accurate machine-learned Hamiltonians for next-generation device-scale modeling
Anubhab Haldar, Ali K. Hamze, Nikhil Sivadas, Yongwoo Shin
https://arxiv.org/abs/2506.10298

GEARS H: Accurate machine-learned Hamiltonians for next-generation device-scale modeling
We introduce GEARS H, a state-of-the-art machine-learning Hamiltonian framework for large-scale electronic structure simulations. Using GEARS H, we present a statistical analysis of the hole concentration induced in defective $\mathrm{WSe}_2$ interfaced with Ni-doped amorphous $\mathrm{HfO}_2$ as a function of the Ni doping rate, system density, and Se vacancy rate in 72 systems ranging from 3326 to 4160 atoms-a quantity and scale of interface electronic structure calculation beyond the reach o…

Automated Treatment Planning for Interstitial HDR Brachytherapy for Locally Advanced Cervical Cancer using Deep Reinforcement Learning
Mohammadamin Moradi, Runyu Jiang, Yingzi Liu, Malvern Madondo, Tianming Wu, James J. Sohn, Xiaofeng Yang, Yasmin Hasan, Zhen Tian
https://arxiv.org/abs/2506.11957…

Automated Treatment Planning for Interstitial HDR Brachytherapy for Locally Advanced Cervical Cancer using Deep Reinforcement Learning
High-dose-rate (HDR) brachytherapy plays a critical role in the treatment of locally advanced cervical cancer but remains highly dependent on manual treatment planning expertise. The objective of this study is to develop a fully automated HDR brachytherapy planning framework that integrates reinforcement learning (RL) and dose-based optimization to generate clinically acceptable treatment plans with improved consistency and efficiency. We propose a hierarchical two-stage autoplanning framework.…

This https://arxiv.org/abs/2407.19353 has been replaced.
initial toot: https://mastoxiv.page/@arX…

A spring-block theory of feature learning in deep neural networks
Feature-learning deep nets progressively collapse data to a regular low-dimensional geometry. How this emerges from the collective action of nonlinearity, noise, learning rate, and other factors, has eluded first-principles theories built from microscopic neuronal dynamics. We exhibit a noise-nonlinearity phase diagram that identifies regimes where shallow or deep layers learn more effectively and propose a macroscopic mechanical theory that reproduces the diagram and links feature learning acr…

This https://arxiv.org/abs/2502.03701 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

First-ish Order Methods: Hessian-aware Scalings of Gradient Descent
Gradient descent is the primary workhorse for optimizing large-scale problems in machine learning. However, its performance is highly sensitive to the choice of the learning rate. A key limitation of gradient descent is its lack of natural scaling, which often necessitates expensive line searches or heuristic tuning to determine an appropriate step size. In this paper, we address this limitation by incorporating Hessian information to scale the gradient direction. By accounting for the curvatur…

FERRET: Private Deep Learning Faster And Better Than DPSGD
David Zagardo
https://arxiv.org/abs/2506.05416 https://arxiv.org/pdf/2506.…

FERRET: Private Deep Learning Faster And Better Than DPSGD
We revisit 1-bit gradient compression through the lens of mutual-information differential privacy (MI-DP). Building on signSGD, we propose FERRET--Fast and Effective Restricted Release for Ethical Training--which transmits at most one sign bit per parameter group with Bernoulli masking. Theory: We prove each fired group leaks at most ln 2 nats; after subsampling with rate s, the total privacy loss of G groups trained for T steps with firing probability p is epsilon = G * T * s * p * ln 2. Thu…

A Start To End Machine Learning Approach To Maximize Scientific Throughput From The LCLS-II-HE
Aashwin Mishra, Matt Seaberg, Ryan Roussel, Fred Poitevin, Jana Thayer, Daniel Ratner, Auralee Edelen, Apurva Mehta
https://arxiv.org/abs/2505.23858

A Start To End Machine Learning Approach To Maximize Scientific Throughput From The LCLS-II-HE
With the increasing brightness of Light sources, including the Diffraction-Limited brightness upgrade of APS and the high-repetition-rate upgrade of LCLS, the proposed experiments therein are becoming increasingly complex. For instance, experiments at LCLS-II-HE will require the X-ray beam to be within a fraction of a micron in diameter, with pointing stability of a few nanoradians, at the end of a kilometer-long electron accelerator, a hundred-meter-long undulator section, and tens of meters l…

Stochastic gradient descent based variational inference for infinite-dimensional inverse problems
Jiaming Sui, Junxiong Jia, Jinglai Li
https://arxiv.org/abs/2506.08380

Stochastic gradient descent based variational inference for infinite-dimensional inverse problems
This paper introduces two variational inference approaches for infinite-dimensional inverse problems, developed through gradient descent with a constant learning rate. The proposed methods enable efficient approximate sampling from the target posterior distribution using a constant-rate stochastic gradient descent (cSGD) iteration. Specifically, we introduce a randomization strategy that incorporates stochastic gradient noise, allowing the cSGD iteration to be viewed as a discrete-time process.…

COSMOS-Web: Estimating Physical Parameters of Galaxies Using Self-Organizing Maps
Fatemeh Abedini, Ghassem Gozaliasl, Akram Hasani Zonoozi, Atousa Kalantari, Maarit Korpi-Lagg, Olivier Ilbert, Hollis B. Akins, Natalie Allen, Rafael C. Arango-Toro, Caitlin M. Casey, Nicole E. Drakos, Andreas L. Faisst, Carter Flayhart, Maximilien Franco, Santosh Harish, Hossein Hatamnia, Jeyhan S. Kartaltepe, Ali Ahmad Khostovan, Anton M. Koekemoer, Vasily Kokorev, Rebecca L. Larson, Gavin Leroy, Daizho…

COSMOS-Web: Estimating Physical Parameters of Galaxies Using Self-Organizing Maps
The COSMOS-Web survey, with its unparalleled combination of multiband data -- particularly near-infrared imaging from JWST's NIRCam (F115W, F150W, F277W, and F444W), provides a transformative dataset reaching down to approximately 28th magnitude (F444W) for studying galaxy evolution. In this work, we employ Self-Organizing Maps (SOMs), an unsupervised machine learning method, to estimate key physical parameters of galaxies, redshift, stellar mass, star formation rate (SFR), specific SFR (sSFR),…

On the Benefits of Accelerated Optimization in Robust and Private Estimation
Laurentiu Andrei Marchis, Po-Ling Loh
https://arxiv.org/abs/2506.03044 https:/…

On the Benefits of Accelerated Optimization in Robust and Private Estimation
We study the advantages of accelerated gradient methods, specifically based on the Frank-Wolfe method and projected gradient descent, for privacy and heavy-tailed robustness. Our approaches are as follows: For the Frank-Wolfe method, our technique is based on a tailored learning rate and a uniform lower bound on the gradient of the $\ell_2$-norm over the constraint set. For accelerating projected gradient descent, we use the popular variant based on Nesterov's momentum, and we optimize our obje…

Achieving Linear Speedup and Near-Optimal Complexity for Decentralized Optimization over Row-stochastic Networks
Liyuan Liang, Xinyi Chen, Gan Luo, Kun Yuan
https://arxiv.org/abs/2506.04600

Achieving Linear Speedup and Near-Optimal Complexity for Decentralized Optimization over Row-stochastic Networks
A key challenge in decentralized optimization is determining the optimal convergence rate and designing algorithms to achieve it. While this problem has been extensively addressed for doubly-stochastic and column-stochastic mixing matrices, the row-stochastic scenario remains unexplored. This paper bridges this gap by introducing effective metrics to capture the influence of row-stochastic mixing matrices and establishing the first convergence lower bound for decentralized learning over row-sto…

This https://arxiv.org/abs/2410.13738 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

Instance-dependent Convergence Theory for Diffusion Models
Score-based diffusion models have demonstrated outstanding empirical performance in machine learning and artificial intelligence, particularly in generating high-quality new samples from complex probability distributions. Improving the theoretical understanding of diffusion models, with a particular focus on the convergence analysis, has attracted significant attention. In this work, we develop a convergence rate that is adaptive to the smoothness of different target distributions, referred to …

This https://arxiv.org/abs/2311.16593 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Empowering COVID-19 Detection: Optimizing Performance Through Fine-Tuned EfficientNet Deep Learning Architecture
The worldwide COVID-19 pandemic has profoundly influenced the health and everyday experiences of individuals across the planet. It is a highly contagious respiratory disease requiring early and accurate detection to curb its rapid transmission. Initial testing methods primarily revolved around identifying the genetic composition of the coronavirus, exhibiting a relatively low detection rate and requiring a time-intensive procedure. To address this challenge, experts have suggested using radiolo…

This https://arxiv.org/abs/2504.18268 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Towards a deep learning approach for classifying treatment response in glioblastomas
Glioblastomas are the most aggressive type of glioma, having a 5-year survival rate of 6.9%. Treatment typically involves surgery, followed by radiotherapy and chemotherapy, and frequent magnetic resonance imaging (MRI) scans to monitor disease progression. To assess treatment response, radiologists use the Response Assessment in Neuro-Oncology (RANO) criteria to categorize the tumor into one of four labels based on imaging and clinical features: complete response, partial response, stable dise…

This https://arxiv.org/abs/2111.06931 has been replaced.
link: https://scholar.google.com/scholar?q=a

Kaczmarz and Gauss-Seidel Algorithms with Volume Sampling
The method of Alternating Projections (AP) is a fundamental iterative technique with applications to problems in machine learning, optimization and signal processing. Examples include the Gauss-Seidel algorithm which is used to solve large-scale regression problems and the Kaczmarz and projections onto convex sets (POCS) algorithms that are fundamental to iterative reconstruction. Progress has been made with regards to the questions of efficiency and rate of convergence in the randomized settin…