Machine Learning

Papers filed under cs.LG on arXiv, each one already summarized by Paperlayer. Open any of them to read the summary beside the original PDF, with every point linked to the line, figure, or table it came from.

Search paper metadata (including unsummarized papers)

7,381 to 7,440 of 20,205

The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning
Shivam Agarwal, Zimin Zhang, Lifan Yuan +2
cs.LGcs.AIarXiv:2505.15134v12025
The CMA Evolution Strategy: A Tutorial
Nikolaus Hansen
cs.LGstat.MLarXiv:1604.00772v22016
Adaptive Keyframe Sampling for Long Video Understanding
Xi Tang, Jihao Qiu, Lingxi Xie +3
cs.CVcs.AIcs.LGarXiv:2502.21271v12025
Learning to Reason without External Rewards
Xuandong Zhao, Zhewei Kang, Aosong Feng +2
cs.LGcs.CLarXiv:2505.19590v52025
Graying the black box: Understanding DQNs
Tom Zahavy, Nir Ben Zrihem, Shie Mannor
cs.LGcs.AIcs.NEarXiv:1602.02658v42016
Generative Modelling With Inverse Heat Dissipation
Severi Rissanen, Markus Heinonen, Arno Solin
cs.CVcs.LGstat.MLarXiv:2206.13397v72022
Model-Based Active Exploration
Pranav Shyam, Wojciech Jaśkowski, Faustino Gomez
cs.LGcs.AIcs.ITarXiv:1810.12162v52018
A Confidence-Based Approach for Balancing Fairness and Accuracy
Benjamin Fish, Jeremy Kun, Ádám D. Lelkes
cs.LGcs.CYarXiv:1601.05764v12016
Steering Your Diffusion Policy with Latent Space Reinforcement Learning
Andrew Wagenmaker, Mitsuhiko Nakamoto, Yunchu Zhang +5
cs.ROcs.LGarXiv:2506.15799v22025
MARS: Markov Molecular Sampling for Multi-objective Drug Discovery
Yutong Xie, Chence Shi, Hao Zhou +4
q-bio.BMcs.CEcs.LGarXiv:2103.10432v12021
How much does your data exploration overfit? Controlling bias via information usage
Daniel Russo, James Zou
stat.MLcs.LGarXiv:1511.05219v32015
Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model
Benjamin Letham, Cynthia Rudin, Tyler H. McCormick +1
stat.APcs.LGstat.MLarXiv:1511.01644v12015
Tensorizing Neural Networks
Alexander Novikov, Dmitry Podoprikhin, Anton Osokin +1
cs.LGcs.NEarXiv:1509.06569v22015
Probabilistic Numerics and Uncertainty in Computations
Philipp Hennig, Michael A Osborne, Mark Girolami
math.NAcs.AIcs.LGarXiv:1506.01326v12015
Mini-Batch Semi-Stochastic Gradient Descent in the Proximal Setting
Jakub Konečný, Jie Liu, Peter Richtárik +1
cs.LGstat.MLarXiv:1504.04407v22015
S-matrix informed neural networks for amplitude analysis
Wyatt A. Smith, Arkaitz Rodas, Marius D. Thomas +5
hep-phcs.LGnucl-tharXiv:2608.23750v12026
Gaussian Processes for Data-Efficient Learning in Robotics and Control
Marc Peter Deisenroth, Dieter Fox, Carl Edward Rasmussen
stat.MLcs.LGcs.ROarXiv:1502.02860v22015
Exact tensor completion using t-SVD
Zemin Zhang, Shuchin Aeron
cs.LGmath.NAstat.MLarXiv:1502.04689v22015
GRACE:Gradient-guided Coreset Selection for LLM Unlearning
Praveen Bushipaka, Andrea D'Angelo, Lucia Passaro +1
cs.AIcs.LGarXiv:2608.28361v12026
Effective Learning Rate Governs Loss Dynamics in Language Model Pretraining
Zihan Liu, Ruiheng Zheng, Shaobo Zhang +4
cs.LGarXiv:2608.24814v12026
Robust Data-Collection Policy Learning for Low-Variance Online Policy Evaluation
Claire Chen, Shuze Daniel Liu, Licheng Luo +3
cs.LGstat.MLarXiv:2608.24146v12026
A Data-dependent Early Stopping Rule using Rademacher Complexity with L1-norm
Duy Hoang, Bastien Berret, Olivier Bruneau +1
cs.LGarXiv:2608.24210v12026
Generalization, memorization, and overfitting for diffusion models trained in the lazy high-dimensional regime
Hugo Latourelle-Vigeant, Sinho Chewi, Aram-Alexandre Pooladian +2
stat.MLcs.LGmath.STarXiv:2608.23938v12026
Revenge of Monosemanticity: Specialized Neurons Improve Data Efficiency in MLPs
Amirhesam Abedsoltan, Enric Boix-Adsera, Fivos Kalogiannis +1
cs.LGstat.MLarXiv:2608.24007v12026
RAGSentinel: Certifiable Geometric Consensus for Robust Retrieval-Augmented Generation
Yueyang Quan, Anjun Gao, Yufei Xia +2
cs.CRcs.AIcs.IRarXiv:2608.23965v12026
MnemoDyn: Learning Resting State Dynamics from 40K FMRI sequences
Sourav Pal, Viet Luong, Hoseok Lee +5
cs.LGarXiv:2608.23936v12026
Dataset Complexity Shapes Finite-Distance Loss Geometry in Neural Networks
Jaeyong Bae, Hawoong Jeong
cond-mat.dis-nncond-mat.stat-mechcs.LGarXiv:2608.22361v12026
RAD: Rule-Augmented Relational Anomaly Detection
Noah Dahle, Anne Tumlin, Ngoc Tran +2
cs.LGcs.CRcs.DBarXiv:2608.23468v12026
Beyond Point Predictions: Uncertainty-Aware Satellite Poverty Mapping for Public Policy
Markus B. Pettersson, James Bailie, Mohammad Kakooei +2
cs.LGarXiv:2608.23322v12026
The Price of Decentralization in Top-$K$ Arm Identification
Larissa Xu, Jasmine Nguyen, William Chang
cs.LGarXiv:2608.22120v12026
Gated Decoupled Compositional Bandits: A Unified Theory of Contextual Bandits with Supervised-Calibrated Action Scaling and Pre-Execution Gating
Oleg Miroshnichenko
cs.LGarXiv:2608.21993v12026
Magnitude Homology Is the Associated Graded of the Length Filtration
Luciano Melodia
math.ATcs.CGcs.LGarXiv:2608.21479v12026
FlatLand: Personalized Graph Federated Learning via Tailored Lorentz Space
Jiahong Liu, Ram Samarth B B, Xinyu Fu +4
cs.LGarXiv:2608.21096v12026
Thermo-FL: Thermal-Aware Robust Federated Fine-Tuning of Large Language Models for Edge AI
Shiva Shrestha, Kazi Shaharair Sharif, Zongxing Xie +3
cs.LGcs.DCarXiv:2608.21172v12026
Nothing Changed but the Model: CellFill -- Bounded In-Cell Learning for Bit-Identical, Revocable Updates to Quantized LLMs
Zifeng Liu, Zhiyong Du, Yaxin Lu +4
cs.LGarXiv:2608.20873v12026
Online Optimization : Competing with Dynamic Comparators
Ali Jadbabaie, Alexander Rakhlin, Shahin Shahrampour +1
cs.LGmath.OCstat.MLarXiv:1501.06225v12015
RiskTraf: Risk-Extrapolated Residual Learning for Multi-Variate Traffic Flow Prediction
Guangyu Wang, Zhidan Liu
cs.LGcs.AIarXiv:2608.20656v12026
Reinforcement Learning for Continuous-Time Jump Markov Decision Processes with Applications to Network Dynamic Pricing
Huiling Meng, Ningyuan Chen, Xuefeng Gao
cs.LGarXiv:2608.20680v12026
Conditional-Independence-Regularized Distributional Autoencoders for Mixed-Type Data
Siyuan Tang, Gongjun Xu, Ji Zhu
stat.MEcs.LGstat.MLarXiv:2608.20562v12026
From Inference to Adaptation: A Unified Optimal Transport View of Vision Language Model
Qi Yu, Zhichen Zeng, Katherine Tieu +8
cs.CVcs.AIcs.CLarXiv:2608.18339v12026
Machine Learning for Neuroimaging with Scikit-Learn
Alexandre Abraham, Fabian Pedregosa, Michael Eickenberg +6
cs.LGcs.CVstat.MLarXiv:1412.3919v12014
Minimax Optimality of Score-Entropy Discrete Diffusion
Cholyeon Cho, Yuchen Wu
stat.MLcs.LGarXiv:2608.20635v12026
Stored in Optimizer State, Valued by Later Training: A Causal Account of Subliminal Trait Transfer
Qinyang Xu
cs.LGarXiv:2608.20442v12026
Convex Optimization for Big Data
Volkan Cevher, Stephen Becker, Mark Schmidt
math.OCcs.LGstat.MLarXiv:1411.0972v12014
The concentration game: Bayesian updating, regret, and information
Akshay Balsubramani
cs.LGcs.GTmath.PRarXiv:2608.18061v12026
Debiased Inference for AI-Generated Data without Gold-Standard Labels: Identification via Multiple Imperfect Measurements
Naoki Egami, Sooahn Shin
stat.MEcs.AIcs.CLarXiv:2608.18294v12026
Against Political Polarization: A Unified Framework for Tracing Evolving Political Ideologies on Social Media
Yijie Xu, Chao Wang, Hui Xiong
cs.SIcs.AIcs.CLarXiv:2608.17987v12026
Learning to Execute
Wojciech Zaremba, Ilya Sutskever
cs.NEcs.AIcs.LGarXiv:1410.4615v32014
Dynamic Compression in Recurrent Networks
Jyothish Pari, Ryan Bahlous-Boldi, Pulkit Agrawal
cs.LGarXiv:2608.17896v12026
Policy-Invariant Reward Shaping from LLM Feedback: A Framework for Hybrid RL Agents
Christophe D. Hounwanou, John Emeka Eze, Yaé U. Gaba
cs.LGcs.AIarXiv:2608.18008v12026
A Residual Learning Approach for Unsteady Aerodynamic Load Prediction
Divya Sanghi, Carlos E. S. Cesnik
physics.flu-dyncs.LGarXiv:2608.17894v12026
Leveraging Association Context Retrieval in Knowledge Edit- ing to Build White-Box Attacks on LLMs
Roman Maksimov, Vladimir Aletov, Vladimir Solodkin +3
cs.LGarXiv:2608.17836v12026
Picard Proximal Monte Carlo for Parallel Bayesian Imaging with Score-Based Generative Priors
Deliang Wei, Evan Bell, Wenhan Guo +2
cs.LGarXiv:2608.17666v12026
SPACE: Sample-cloud Predictive Adaptive Conformal Ellipsoids for Multivariate Time-Series Forecasting
Baishi Li, Kelvin J. L. Koa, Ke-Wei Huang
stat.MLcs.AIcs.LGarXiv:2608.17333v12026
Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL
Yunhao Yang, Yuexin Bian, Yunjie Tian +6
cs.LGcs.AIcs.CVarXiv:2608.17253v12026
Certified but Private: Scalable Zero-Knowledge Proofs for Neural Network Guarantees
Youwei Zhong, Ben Merbaum, Timos Antonopoulos +4
cs.LGcs.CRcs.LOarXiv:2608.17070v12026
LiD-GLM: Lipschitz-constrained Deep Generalized Linear Models
Tom Splittgerber, Niklas Koenen, Marvin N. Wright +1
stat.MLcs.LGarXiv:2608.16340v12026
Spectral Gaps of Hit-and-Run and Coordinate Hit-and-Run
Yunbum Kook, Santosh S. Vempala
cs.DScs.LGmath.PRarXiv:2608.16878v12026
SoftModel: A Neural Model That Grows Its Own Topology -- Governed Structural Growth for Continual In-Service Learning
Zhoumin Xie
cs.LGarXiv:2608.16409v12026
Density-Reweighted Entropic Optimal Transport: Decoupling Geometry from Sampling Density
Keyi Li, Yuval Kluger, Boris Landa
stat.MLcs.LGstat.AParXiv:2608.16506v12026

Machine Learning

The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning

The CMA Evolution Strategy: A Tutorial

Adaptive Keyframe Sampling for Long Video Understanding

Learning to Reason without External Rewards

Graying the black box: Understanding DQNs

Generative Modelling With Inverse Heat Dissipation

Model-Based Active Exploration

A Confidence-Based Approach for Balancing Fairness and Accuracy

Steering Your Diffusion Policy with Latent Space Reinforcement Learning

MARS: Markov Molecular Sampling for Multi-objective Drug Discovery

How much does your data exploration overfit? Controlling bias via information usage

Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model

Tensorizing Neural Networks

Probabilistic Numerics and Uncertainty in Computations

Mini-Batch Semi-Stochastic Gradient Descent in the Proximal Setting

S-matrix informed neural networks for amplitude analysis

Gaussian Processes for Data-Efficient Learning in Robotics and Control

Exact tensor completion using t-SVD

GRACE:Gradient-guided Coreset Selection for LLM Unlearning

Effective Learning Rate Governs Loss Dynamics in Language Model Pretraining

Robust Data-Collection Policy Learning for Low-Variance Online Policy Evaluation

A Data-dependent Early Stopping Rule using Rademacher Complexity with L1-norm

Generalization, memorization, and overfitting for diffusion models trained in the lazy high-dimensional regime

Revenge of Monosemanticity: Specialized Neurons Improve Data Efficiency in MLPs

RAGSentinel: Certifiable Geometric Consensus for Robust Retrieval-Augmented Generation

MnemoDyn: Learning Resting State Dynamics from 40K FMRI sequences

Dataset Complexity Shapes Finite-Distance Loss Geometry in Neural Networks

RAD: Rule-Augmented Relational Anomaly Detection

Beyond Point Predictions: Uncertainty-Aware Satellite Poverty Mapping for Public Policy

The Price of Decentralization in Top-$K$ Arm Identification

Gated Decoupled Compositional Bandits: A Unified Theory of Contextual Bandits with Supervised-Calibrated Action Scaling and Pre-Execution Gating

Magnitude Homology Is the Associated Graded of the Length Filtration

FlatLand: Personalized Graph Federated Learning via Tailored Lorentz Space

Thermo-FL: Thermal-Aware Robust Federated Fine-Tuning of Large Language Models for Edge AI

Nothing Changed but the Model: CellFill -- Bounded In-Cell Learning for Bit-Identical, Revocable Updates to Quantized LLMs

Online Optimization : Competing with Dynamic Comparators

RiskTraf: Risk-Extrapolated Residual Learning for Multi-Variate Traffic Flow Prediction

Reinforcement Learning for Continuous-Time Jump Markov Decision Processes with Applications to Network Dynamic Pricing

Conditional-Independence-Regularized Distributional Autoencoders for Mixed-Type Data

From Inference to Adaptation: A Unified Optimal Transport View of Vision Language Model

Machine Learning for Neuroimaging with Scikit-Learn

Minimax Optimality of Score-Entropy Discrete Diffusion

Stored in Optimizer State, Valued by Later Training: A Causal Account of Subliminal Trait Transfer

Convex Optimization for Big Data

The concentration game: Bayesian updating, regret, and information

Debiased Inference for AI-Generated Data without Gold-Standard Labels: Identification via Multiple Imperfect Measurements

Against Political Polarization: A Unified Framework for Tracing Evolving Political Ideologies on Social Media

Learning to Execute

Dynamic Compression in Recurrent Networks

Policy-Invariant Reward Shaping from LLM Feedback: A Framework for Hybrid RL Agents

A Residual Learning Approach for Unsteady Aerodynamic Load Prediction

Leveraging Association Context Retrieval in Knowledge Edit- ing to Build White-Box Attacks on LLMs

Picard Proximal Monte Carlo for Parallel Bayesian Imaging with Score-Based Generative Priors

SPACE: Sample-cloud Predictive Adaptive Conformal Ellipsoids for Multivariate Time-Series Forecasting

Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL

Certified but Private: Scalable Zero-Knowledge Proofs for Neural Network Guarantees

LiD-GLM: Lipschitz-constrained Deep Generalized Linear Models

Spectral Gaps of Hit-and-Run and Coordinate Hit-and-Run

SoftModel: A Neural Model That Grows Its Own Topology -- Governed Structural Growth for Continual In-Service Learning

Density-Reweighted Entropic Optimal Transport: Decoupling Geometry from Sampling Density