Convergence

Follow this topic Ask about this topic

Momentum

51 papers in the last four weeks, up 155% on the four weeks before. 0.5% of all new papers.

Jul 13Week of Sep 28

Latest papers 390

All topics

Asynchronous LLM Post-Training: Group-Mass Capping and Convergence Analysis
Oct 1, 2026Qijia He, Ruinan Jin, Jun Luo +2Convergence Trajectory-Level Credit
The Ohio State University · Arizona State University
Participation-Sensitive Convergence and the Fragment First, Converge Later Pattern in Asynchronous Online Learning: A Topological Analysis Across 22 OULAD Courses
Oct 1, 2026Hitoshi Inoue, Koichi YasutakeParticipation Cohort
Nakamura Gakuen University, Japan · Hiroshima University, Japan
Convergence Analysis of STORM Under Different Geometries
Oct 1, 2026Wei Jiang, Yibo Wang, Wenhao Yang +3Stochastic Convex Optimization Convex Optimization
School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China · School of Artificial Intelligence, Nanjing University, Nanjing, China
Convergence of Practical Muon with Finite Newton-Schulz Iterations and Nesterov Momentum
Sep 30, 2026Hanyng Peng, Hui Wang, Yue YuMomentum Stochastic Gradient Descent Newton
Pengcheng Laboratory, Shenzhen, China
GRPO Training Dynamics for Small Language Models
Sep 30, 2026Rajat Ghosh, Vaishnavi Bhargava, Henry Wong +2Convergence
Nutanix
Client and Training Data Selection for Computationally Efficient Synchronized Federated Learning
Sep 30, 2026Muzaffer Citir, Hiroki Nishikawa, Sangyoung ParkFederated Learning Training Data
Smart Mobility Systems, Technical University of Berlin, Germany · Graduate School of Information Science and Technology, The University of Osaka, Japan
DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence
Sep 30, 2026Xu Huang, Ye Huang, Zijun Liao +6Generative Image Compression Token Compression
Peking University · Singapore University of Technology and Design
The Advantages of Fresh Sketching for Ridge Regression
Sep 29, 2026Linkai Ma, Qilin Li, Petros DrineasKernel Ridge Regression Sketches
Purdue University · University of Wisconsin-Madison
Adam under Generalized Smoothness with Second-Moment-Type Stochastic Gradients
Sep 29, 2026Ruinan Jin, Difei Cheng, Ling Chen +3Smoothness Adam
Mohamed bin Zayed University of Artificial Intelligence · Aerospace Information Technology University · The Ohio State University +2
Principled MAP estimation for inverse problems: bridging the gap between convergence and performance
Sep 29, 2026Alexandre Lagier, Valentine Tosel, Anne Gagneux +2Bayesian Inverse Problems Iterative Denoising Methods
ENS de Lyon, CNRS, Université Claude Bernard Lyon 1, Inria, LIP UMR 5668, 69342 Lyon Cedex 07, France · Univ. Bordeaux, Inria, Bordeaux INP, IMB, UMR 5251, F-33400 Talence, France · Inria, ENS de Lyon, CNRS, Université Claude Bernard Lyon 1, LIP UMR 5668, 69342 Lyon Cedex 07, France
MeqMuon: Matrix-Equilibrating Muon for LLM Pretraining
Sep 28, 2026Chang-Wei Shi, Xu Wang, Wu-Jun LiLarge Language Model Pretraining Muon
National Key Laboratory for Novel Software Technology, School of Computer Science, Nanjing University, P. R. China
An analysis of Mirror-Descent Soft Actor-Critic
Sep 28, 2026Denis Zorba, Michal ValkoMirror Descent Soft Actor-Critic
School of Mathematics, University of Edinburgh, United Kingdom · INRIA, Paris, France
Bregman Consensus
Sep 28, 2026Andrei N. SoklakovBregman Divergences Collective Behaviors
Finite-Time Concentration and Convergence Rates for Projected Two-Time-Scale Stochastic Approximation with Markov Noise
Sep 28, 2026Rahul Singh, Vivek S. Borkar, Eric MoulinesStochastic Approximation Convergence
Laboratoire de Recherche de l’EPITA, Paris, France · Indian Institute of Technology Bombay · Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates
Minimax Last-Iterate Convergence in Matrix Games with Observed Actions
Sep 28, 2026Yuheng ZhangImperfect-Information Games Minimax
University of Illinois Urbana-Champaign
The Model Knows When to Stop: Training-Free Early Stopping for Long-Context Reading
Sep 28, 2026Muath Alyobi, Mohamed Eltahir, Almoayyad Abuljdail +3Efficient Long-Context Inference Long-Context Reasoning
King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia · Department of Computer Science, Edge Hill University, Ormskirk, England
Convergent Plug-and-Play Image Restoration with Annealed Noise Levels
Sep 26, 2026Samuel HuraultImage Restoration Iterative Denoising Methods
LIGM, CNRS, Univ. Gustave Eiffel
Averaged Mirror Descent and Dual Gradient Methods: Convergent Algorithms for Entropic Gromov-Wasserstein Problems
Sep 25, 2026Joanna Marks, Gabriel Rioux, Riccardo PasseggeriGromov--Wasserstein Mirror Descent
⋆Denotes equal contribution to this work.
Precise Convergence Speed of Clipped SGD
Sep 24, 2026David A. R. RobinGradient Descent Convergence
LAMSADE, Université Paris-Dauphine, PSL Research University
SPADE-DFL: Communication-Efficient Decentralized Federated Learning via Derivative-Free Linearized ADMM
Sep 24, 2026Mengli Wei, Mengkai Zhu, Jiawen Chen +2Decentralized Learning Federated Learning
School of Mathematics, Southeast University, Nanjing 210096, China
Low-Rank Friction for Memory-Efficient Transformer Pretraining
Sep 24, 2026Rajit Rajpal, Benedict LeimkuhlerAdam Transformer Architectures
School of Mathematics University of Edinburgh Edinburgh, UK EH9 3FD
Local Geometric Mixing via Dobrushin Contraction with Applications to Diffusion Path Monte Carlo and the Proximal Sampler
Sep 23, 2026Stefan OberdörsterMarkov Chain Monte Carlo Convergence
Institute for Applied Mathematics, University of Bonn
EBRL: Asynchronous Embodied RL by Multi-Grained Resource Management
Sep 23, 2026Liang Mi, Weijun Wang, Bowen Gao +12Offline Reinforcement Learning Convergence
Nanjing University · Institute for AI Industry Research (AIR), Tsinghua University · Nanjing University of Posts and Telecommunications +1
What Converges in the Platonic Representation Hypothesis? Structure over Geometry
Sep 23, 2026Junwon You, Mihyun Jang, Sangwoo Mo +1Representational Similarity Analysis Convergence
KAIST · POSTECH
Sharp Convergence of Wasserstein Gradient Flows for Spectrally Nonnegative Interaction Energies
Sep 22, 2026Zhengjiang Lin, Philippe RigolletWasserstein Gradient Flows Logarithmic Sobolev Inequalities
Statistical Rates for Entropic Optimal Transport in the Discrete to SubGaussian Regime
Sep 22, 2026Tomas Gonzalez, Gonzalo MenaOptimal Transport Approach Non-Gaussianity
Department of Machine Learning, Carnegie Mellon University · Department of Statistics & Data Science, Carnegie Mellon University
Polyak-Type Extragradient Methods for Monotone Root-Finding Problems
Sep 22, 2026TaeHo Yoon, Sayantan Choudhury, Ezra Greenberg +1Monotone Variational Inequalities Convergence
Department of Applied Mathematics & Statistics Mathematical Institute for Data Science (MINDS) Johns Hopkins University
Behavior is Not Enough: A Mechanism-Based Evaluation of Social Norm Emergence in LLM Societies
Sep 22, 2026Rasika Muralidharan, Haewoon Kwak, Jisun AnSocial Dynamics Social Norms
Indiana Univeristy Bloomington
Reciprocal Collaboration: how lessons from convergence in GLAMs can enhance interdisciplinary AI research
Sep 22, 2026Amber L. Cushing, Suzanne Little, Giulia OstiInterdisciplinary Research Human-Ai Collaboration
School of Information & Communication Studies, University College Dublin, Ireland · School of Computing, Dublin City University, Ireland
Neural Approximation by Function Composition: Rigidity and Doubly Exponential Convergence
Sep 22, 2026Wentao Huang, Haizhang ZhangNeural Approximations Approximation
Department of Mathematics, The University of Hong Kong, Hong Kong, P.R. China. · School of Mathematics, Sun Yat-sen University, Guangzhou, P.R. China.
Guaranteed Low-Rank Tensor Recovery from Modewise Measurements via Normalized Block-Weighted Riemannian Gradient Descent
Sep 21, 2026Yushi Zhou, Feng ZhangLow-Rank Structure Convergence
School of Mathematics and Statistics, Southwest University, Chongqing, China.
Adaptive Determinantal Client Scheduling in Federated Learning
Sep 20, 2026Wen Xu, Ben Liang, Gary Boudreau +1Federated Learning Schedulers
University of Toronto, Canada · Ericsson, Canada
Statistical Convergence of Transformer Encoder-Accelerated Robust Reinforcement Learning
Sep 20, 2026Suman Banerjee, Hiroyasu TsukamotoOffline Reinforcement Learning Value Functions
Department of Aerospace Engineering, The Grainger College of Engineering, University of Illinois Urbana-Champaign, Urbana, IL, USA
The First-Order Oracle Complexity of Lipschitz Convex Optimization in Nondual Settings
Sep 17, 2026David Martínez-Rubio, Brian Bullins, Cristóbal Guzmán +1Convex Optimization Lipschitz Continuity
IMDEA Software Institute, Madrid, Spain · Purdue University, West Lafayette, IN, USA · Institute for Mathematical and Computational Engineering, Faculty of Mathematics and School of Engineering, Pontificia Universidad Católica de Chile, Santiago, Chile +1
Near-Optimal Single-Loop Predictor--Corrector Extragradient Method for Strongly Convex--Strongly Concave Minimax Optimization
Sep 17, 2026Minhao Zhang, Zi XuConvex Optimization Convergence
Department of Mathematics, Shanghai University, Shanghai 200444, People’s Republic of China
A Convergence Framework for Deep $V$ -Learning: Error Propagation and Sharp Action-Gap Bounds
Sep 16, 2026Yury KolomeytsevValue Functions Optimal Learner
Faculty of Computational Mathematics and Cybernetics Lomonosov Moscow State University
Revisiting Distributed Sign-Based Variance Reduction
Sep 16, 2026Wei Jiang, Zechao Li, Lijun ZhangDecentralized Optimization Variance Reduction
School of Computer Science and Engineering, Nanjing University of Science and Technology, China · National Key Laboratory for Novel Software Technology,Nanjing University, China · School of Artificial Intelligence, Nanjing University, China
Preservation of Log-Concavity and Convergence of Wasserstein-Fisher-Rao Gradient Flows
Sep 16, 2026Francesca Romana Crucinio, Sahani PathirajaWasserstein Gradient Flows Log-Concave Distributions
ESOMAS, University of Turin, Italy & Collegio Carlo Alberto, Turin, Italy · School of Mathematics & Statistics, UNSW Sydney, Australia
How I learned to stop worrying and love StopGrads: Stationarity, Convergence, and a case study on Flow Map Learning
Sep 14, 2026Max W. Shen, Mark Goldstein, Zichu Wang +2Wasserstein Gradient Flows Flow Map
Flatiron Institute · NYU
The fixed-point bundle method over product-of-simplex domains arising from game equilibria
Sep 14, 2026Hongbo SunMonotone Variational Inequalities Nash Equilibrium
Hongbo Sun∗
Self-Evolving Memory for Generative Recommendation
Sep 14, 2026Xinyu Lin, Zhuosong Jiang, Zixiao Suo +12Real-World Content Recommendation Problem Recommendation
National University of Singapore · Meta AI
Improving the Last-Iterate Guarantees of Anytime Algorithms for Stochastic Monotone Variational Inequalities
Sep 14, 2026Jun-Hyun Kim, Ahmet AlacaogluMonotone Variational Inequalities Convergence
University of British Columbia, Vancouver. · Department of Mathematics, University of British Columbia, Vancouver.
Convergence rates for generative drifting flows: fixed-scale obstructions and multihead acceleration
Sep 14, 2026Arthur Stéphanovitch, Eddie AamariGenerative Models Convergence
Centre de recherche en économie et statistique · ENSAE, IP Paris · Département de Mathématiques et Applications +1
Convergence of Stochastic Gradient Methods under Heavy-Tailed Noise and H"{o}lder Smoothness
Sep 14, 2026Misbah Uz Zaman, Anirbit MukherjeeStochastic Gradient Descent Lipschitz Continuity
Department of Mathematics and Statistics Indian Institute of Science Education and Research Kolkata · Department of Computer Science The University of Manchester
High-Probability Convergence of SGD via Batched Updates
Sep 14, 2026Feng Zhu, Robert W. Heath Jr., Aritra MitraStochastic Gradient Descent Federated Learning
Steady-State Convergence of Stochastic Approximation
Sep 14, 2026Yixuan Zhang, Qiaomin XieStochastic Approximation Convergence
Department of Industrial & Systems Engineering, University of Wisconsin–Madison
Almost Sure Convergence Analysis of Stochastic Gradient Methods with Clipping and Additive Noise
Sep 10, 2026Amartya Mukherjee, Jun LiuStochastic Gradient Descent Gradient Clipping
Department of Applied Mathematics, University of Waterloo, Waterloo, Ontario, Canada N2L 3G1
Global Divergence, Local Convergence: Representation Geometry in SSMs and Transformers
Sep 8, 2026Amit Ben-Artzy, Roy SchwartzTransformer Architectures Representational Capacity
Computer Science, The Hebrew University of Jerusalem
The Exact Time-Uniform Rate Frontier for Stochastic Gradient Descent on Smooth Convex Objectives
Sep 8, 2026Ruijie Li, Kang Chen, Tianyu WangStochastic Gradient Descent Convergence
School of Data Science, Fudan University · Shanghai Center for Mathematical Sciences, Fudan University
Non-Coherent Over-the-Air Federated Learning: Protocol, Convergence, and Device Scheduling
Sep 8, 2026Haifeng Wen, Nicolò Michelusi, Osvaldo Simeone +2Federated Learning Power Allocation
IoT Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, 511453, China · School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ 85281 USA · Institute for Intelligent Networked Systems, Northeastern University London, London, E1 8PH, UK +2
Parallelism Strategy Chaining for Fast Training Convergence
Sep 7, 2026Minchul Kang, Changyong Shin, Younghun Go +4Large Language Model Training Language Model Perplexity
Department of Computer Science and Engineering, Korea University, Seoul, South Korea
Projected Riemannian Gradient Descent for the Bures-Wasserstein Barycenter: Dimension-Independent Linear Convergence at Unit Step Size
Sep 3, 2026A. AfhamRiemannian Optimization Wasserstein Distance
Centre for Quantum Technologies, National University of Singapore, Singapore
Spectral Convergence of Random Feature Method in Multiple Dimensions
Sep 3, 2026Pingbing Ming, Hao YuAtom-Averaged Features Spectral Representation Method
No-Regret Bayesian Optimization with Finite-Library Input-Warped Kernels
Sep 2, 2026Edvin Ketabati Augustinsson, Robert A. BridgesBayesian Optimization Gaussian Process
AI Sweden, Gothenburg, Sweden
Convergence Theory of Knowledge Distillation in Asynchronous P2P Gossip Learning Network
Sep 1, 2026Lucas Qingyang Fang, Tiyao Liu, Jinhao Jing +4Knowledge Distillation Gossip
University of California, Santa Cruz, USA · China University of Petroleum, China · The Chinese University of Hong Kong, Shenzhen, China +2
Independent Reinforcement Learning in Discounted Markov Games
Sep 1, 2026Asrin Efe Yorulmaz, Ugur Aydin, Tamer BasarMean Field Games Multi-Agent Reinforcement Learning
Department of Electrical and Computer Engineering, University of Illinois Urbana-Champaign, Urbana, IL, 61801, USA
RestoreBench: Can AI Agents Restore Power Flow Convergence?
Aug 31, 2026Riccardo Mansutti, Andrea Pomarico, Robert Jakob +3Power Systems Optimal Power Flow
1ETH Zürich · 2Politecnico di Milano · 3Harvard University
Convergence rates for the RMSprop optimizer with full control of the hyperparameters
Aug 31, 2026Steffen Dereich, Arnulf JentzenAdam Stochastic Convex Optimization
A Globally Convergent Algorithm for Total Scaled-Gradient Variation via Cone-Constrained Bilinear Decomposition
Aug 29, 2026Haibin Su, Chunlin Wu, Huibin Chang +1Image Restoration Convergence
Yau Mathematical Sciences Center, Tsinghua University, Beijing 100084, China · School of Mathematical Sciences, Nankai University, Tianjin, 300071, China · School of Mathematical Sciences and Institute of Mathematics and Interdisciplinary Sciences, Tianjin Normal University, Tianjin, 300387, China
A Finite-Sample Analysis of Quantile Temporal-Difference Learning
Aug 27, 2026Zijie Cheng, Xiang Li, Yang Peng +1Temporal Difference Convergence
School of Mathematical Sciences, Peking University · Perelman School of Medicine, University of Pennsylvania · Yau Mathematical Sciences Center, Tsinghua University

Oct 1, 2026, cs.LGJ/K move · Enter open · S save

Asynchronous LLM Post-Training: Group-Mass Capping and Convergence Analysis

Qijia He, Ruinan Jin, Jun Luo, Shaofeng Zou+1

The Ohio State University · Arizona State University

Convergence Trajectory-Level Credit

Open paper AskPDF arXiv

Asynchronous reinforcement learning (RL) improves the efficiency of large language model post-training but introduces stale rollouts generated by earlier policies. Theoretical understanding of how this staleness affects convergence and how to mitigate its impact remains limited. We derive a convergence bound for GRPO-style algorithms that explicitly characterizes the tradeoff between the gradient estimator's second moment and bias. For trajectory-level importance-weighted estimators, our analysis shows that once the second moment is uniformly controlled, delay enters the bound through the bias introduced by clipping or rescaling. Guided by this insight, we propose a novel group mass capping GRPO (GMC-GRPO) method, which minimizes a ratio-based bias bound within a class of weighted estimators sharing a common second-moment guarantee. We establish convergence guarantees for asynchronous GMC-GRPO and show that, compared with TIC-GRPO, it improves the threshold dependence of the fourth-order delay term from

O(ε^{-4})

O(ε^{-2})

ε\to0

, where

1+ε

is the ratio threshold. Under local policy overlap, the delay-dependent term decreases as

G^{-2/5}

after tuning the step size, where

G

is the group size. For fixed behavior and current policies, the bias introduced by group rescaling also vanishes as

G\to\infty

, whereas the bias from trajectory-wise clipping can persist. Experiments across Qwen3 models and reasoning benchmarks demonstrate improved robustness to stale rollouts, with GMC-GRPO achieving the best performance among stable baselines under large rollout delays.

Momentum

Related topics

Latest papers 390