{"total":199,"rows":[{"id":"2206.06232","title":"Towards Understanding Sharpness-Aware Minimization","created":"2022-06-13","cited_by_count":146,"area":null},{"id":"2202.09357","title":"ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!","created":"2022-02-18","cited_by_count":134,"area":null},{"id":"2503.12645","title":"Understanding Gradient Orthogonalization for Deep Learning via Non-Euclidean Trust-Region Optimization","created":"2025-03-16","cited_by_count":92,"area":null},{"id":"2111.09278","title":"Differentially Private Federated Learning on Heterogeneous Data","created":"2021-11-17","cited_by_count":74,"area":null},{"id":"2108.09020","title":"Online Continual Learning with Natural Distribution Shifts: An Empirical Study with Visual Data","created":"2021-08-20","cited_by_count":69,"area":null},{"id":"2206.07638","title":"Asynchronous SGD Beats Minibatch SGD Under Arbitrary Delays","created":"2022-06-15","cited_by_count":63,"area":null},{"id":"2209.14863","title":"Neural Networks Efficiently Learn Low-Dimensional Representations with SGD","created":"2022-09-29","cited_by_count":63,"area":null},{"id":"2205.13692","title":"FedAvg with Fine Tuning: Local Updates Lead to Representation Learning","created":"2022-05-27","cited_by_count":56,"area":null},{"id":"2106.02969","title":"FedNL: Making Newton-Type Methods Applicable to Federated Learning","created":"2021-06-05","cited_by_count":52,"area":null},{"id":"2210.03403","title":"TAN Without a Burn: Scaling Laws of DP-SGD","created":"2022-10-07","cited_by_count":52,"area":null},{"id":"2205.13648","title":"A Unified Analysis of Federated Learning with Arbitrary Client Participation","created":"2022-05-26","cited_by_count":45,"area":null},{"id":"2107.00052","title":"Stochastic Gradient Descent-Ascent and Consensus Optimization for Smooth Games: Convergence Analysis under Expected Co-coercivity","created":"2021-06-30","cited_by_count":43,"area":null},{"id":"2203.10983","title":"BNS-GCN: Efficient Full-Graph Training of Graph Convolutional Networks with Partition-Parallelism and Random Boundary Node Sampling","created":"2022-03-21","cited_by_count":43,"area":null},{"id":"2305.16296","title":"A Guide Through the Zoo of Biased SGD","created":"2023-05-25","cited_by_count":40,"area":null},{"id":"2206.04723","title":"On the Unreasonable Effectiveness of Federated Averaging with Heterogeneous Data","created":"2022-06-09","cited_by_count":38,"area":null},{"id":"2202.07262","title":"Stochastic Gradient Descent-Ascent: Unified Theory and New Efficient Methods","created":"2022-02-15","cited_by_count":37,"area":null},{"id":"2103.03239","title":"Moshpit SGD: Communication-Efficient Decentralized Training on Heterogeneous Unreliable Devices","created":"2021-03-04","cited_by_count":36,"area":null},{"id":"2102.04396","title":"SGD in the Large: Average-case Analysis, Asymptotics, and Stepsize Criticality","created":"2021-02-08","cited_by_count":35,"area":null},{"id":"2102.06704","title":"Proximal and Federated Random Reshuffling","created":"2021-02-12","cited_by_count":33,"area":null},{"id":"2207.04338","title":"Variance Reduced ProxSkip: Algorithm, Theory and Application to Federated Learning","created":"2022-07-09","cited_by_count":33,"area":null},{"id":"2111.08611","title":"Stochastic Extragradient: General Analysis and Improved Rates","created":"2021-11-16","cited_by_count":31,"area":null},{"id":"2306.03638","title":"Provable convergence guarantees for black-box variational inference","created":"2023-06-04","cited_by_count":29,"area":null},{"id":"2109.14756","title":"A Two-Time-Scale Stochastic Optimization Framework with Applications in Control and Reinforcement Learning","created":"2021-09-29","cited_by_count":24,"area":null},{"id":"2112.13246","title":"Towards Federated Learning on Time-Evolving Heterogeneous Data","created":"2021-12-25","cited_by_count":23,"area":null},{"id":"2206.08829","title":"FedNew: A Communication-Efficient and Privacy-Preserving Newton-Type Method for Federated Learning","created":"2022-06-17","cited_by_count":23,"area":null},{"id":"2402.17457","title":"Super Consistency of Neural Network Landscapes and Learning Rate Transfer","created":"2024-02-27","cited_by_count":23,"area":null},{"id":"2110.15412","title":"Stochastic Mirror Descent: Convergence Analysis and Adaptive Variants via the Mirror Stochastic Polyak Stepsize","created":"2021-10-28","cited_by_count":22,"area":null},{"id":"2112.02089","title":"Regularized Newton Method with Global $O(1/k^2)$ Convergence","created":"2021-12-03","cited_by_count":22,"area":null},{"id":"2212.14370","title":"Can 5th Generation Local Training Methods Support Client Sampling? Yes!","created":"2022-12-29","cited_by_count":22,"area":null},{"id":"2305.15349","title":"On the Convergence of Black-Box Variational Inference","created":"2023-05-24","cited_by_count":22,"area":null},{"id":"2102.09393","title":"On the Convergence of Step Decay Step-Size for Stochastic Optimization","created":"2021-02-18","cited_by_count":21,"area":null},{"id":"2104.09342","title":"Random Reshuffling with Variance Reduction: New Analysis and Better Rates","created":"2021-04-19","cited_by_count":19,"area":null},{"id":"2106.11851","title":"Stochastic Polyak Stepsize with a Moving Target","created":"2021-06-22","cited_by_count":19,"area":null},{"id":"2204.12446","title":"Beyond Lipschitz: Sharp Generalization and Excess Risk Bounds for Full-Batch GD","created":"2022-04-26","cited_by_count":19,"area":null},{"id":"2107.00464","title":"On the Convergence of Stochastic Extragradient for Bilinear Games using Restarted Iteration Averaging","created":"2021-06-30","cited_by_count":18,"area":null},{"id":"2202.12328","title":"Cutting Some Slack for SGD with Adaptive Polyak Stepsizes","created":"2022-02-24","cited_by_count":18,"area":null},{"id":"2209.02257","title":"Faster federated optimization under second-order similarity","created":"2022-09-06","cited_by_count":18,"area":null},{"id":"2210.16402","title":"GradSkip: Communication-Accelerated Local Gradient Methods with Better Computational Complexity","created":"2022-10-28","cited_by_count":18,"area":null},{"id":"2109.04522","title":"Asynchronous Iterations in Optimization: New Sequence Results and Sharper Algorithmic Guarantees","created":"2021-09-09","cited_by_count":17,"area":null},{"id":"2504.09951","title":"Towards Weaker Variance Assumptions for Stochastic Optimization","created":"2025-04-14","cited_by_count":17,"area":null},{"id":"2109.05198","title":"Doubly Adaptive Scaled Algorithm for Machine Learning Using Second-Order Information","created":"2021-09-11","cited_by_count":16,"area":null},{"id":"2110.11442","title":"Towards Noise-adaptive, Problem-adaptive (Accelerated) Stochastic Gradient Descent","created":"2021-10-21","cited_by_count":16,"area":null},{"id":"2102.09700","title":"AI-SARAH: Adaptive and Implicit Stochastic Recursive Gradient Methods","created":"2021-02-19","cited_by_count":15,"area":null},{"id":"2402.13794","title":"Revisiting Convergence of AdaGrad with Relaxed Assumptions","created":"2024-02-21","cited_by_count":15,"area":null},{"id":"2103.02062","title":"Variance Reduced Training with Stratified Sampling for Forecasting Models","created":"2021-03-02","cited_by_count":14,"area":null},{"id":"2106.03056","title":"MURANA: A Generic Framework for Stochastic Variance-Reduced Optimization","created":"2021-06-06","cited_by_count":14,"area":null},{"id":"2302.14043","title":"Single-Call Stochastic Extragradient Methods for Structured Non-monotone Variational Inequalities: Improved Analysis under Weaker Conditions","created":"2023-02-27","cited_by_count":14,"area":null},{"id":"2106.13031","title":"Towards Biologically Plausible Convolutional Networks","created":"2021-06-22","cited_by_count":13,"area":null},{"id":"2402.07793","title":"Tuning-Free Stochastic Optimization","created":"2024-02-12","cited_by_count":13,"area":null},{"id":"2406.04142","title":"Stochastic Polyak Step-sizes and Momentum: Convergence Guarantees and Practical Performance","created":"2024-06-06","cited_by_count":13,"area":null},{"id":"2410.08305","title":"Randomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptation","created":"2024-10-10","cited_by_count":13,"area":null},{"id":"2205.03914","title":"Federated Random Reshuffling with Compression and Variance Reduction","created":"2022-05-08","cited_by_count":12,"area":null},{"id":"2307.01497","title":"Accelerated stochastic approximation with state-dependent noise","created":"2023-07-04","cited_by_count":11,"area":null},{"id":"2406.04425","title":"On Regularization via Early Stopping for Least Squares Regression","created":"2024-06-06","cited_by_count":11,"area":null},{"id":"2104.12676","title":"Solving a class of non-convex min-max games using adaptive momentum methods","created":"2021-04-26","cited_by_count":10,"area":null},{"id":"2106.02720","title":"An Even More Optimal Stochastic Optimization Algorithm: Minibatching and Interpolation Learning","created":"2021-06-04","cited_by_count":10,"area":null},{"id":"2108.11483","title":"Heavy-tailed Streaming Statistical Estimation","created":"2021-08-25","cited_by_count":10,"area":null},{"id":"2206.02953","title":"Sampling without Replacement Leads to Faster Rates in Finite-Sum Minimax Optimization","created":"2022-06-07","cited_by_count":10,"area":null},{"id":"2208.13592","title":"Smooth Monotone Stochastic Variational Inequalities and Saddle Point Problems: A Survey","created":"2022-08-29","cited_by_count":10,"area":null},{"id":"2307.14642","title":"Linear Convergence of Black-Box Variational Inference: Should We Stick the Landing?","created":"2023-07-27","cited_by_count":10,"area":null},{"id":"2503.02225","title":"Sharpness-Aware Minimization: General Analysis and Improved Rates","created":"2025-03-04","cited_by_count":10,"area":null},{"id":"2102.08374","title":"IntSGD: Adaptive Floatless Compression of Stochastic Gradients","created":"2021-02-16","cited_by_count":9,"area":null},{"id":"2109.14120","title":"Meta Learning on a Sequence of Imbalanced Domains with Difficulty Awareness","created":"2021-09-29","cited_by_count":8,"area":null},{"id":"2110.03294","title":"EF21 with Bells & Whistles: Six Algorithmic Extensions of Modern Error Feedback","created":"2021-10-07","cited_by_count":8,"area":null},{"id":"2211.08597","title":"SketchySGD: Reliable Stochastic Optimization via Randomized Curvature Estimates","created":"2022-11-16","cited_by_count":8,"area":null},{"id":"2301.06806","title":"Convergence of First-Order Algorithms for Meta-Learning with Moreau Envelopes","created":"2023-01-17","cited_by_count":8,"area":null},{"id":"2306.03240","title":"Improving Accelerated Federated Learning with Compression and Importance Sampling","created":"2023-06-05","cited_by_count":8,"area":null},{"id":"2310.09183","title":"PRIOR: Personalized Prior for Reactivating the Information Overlooked in Federated Learning","created":"2023-10-13","cited_by_count":8,"area":null},{"id":"2103.12293","title":"Stochastic Reweighted Gradient Descent","created":"2021-03-23","cited_by_count":7,"area":null},{"id":"2108.04448","title":"Decentralized Composite Optimization with Compression","created":"2021-08-10","cited_by_count":7,"area":null},{"id":"2111.06171","title":"Convergence and Stability of the Stochastic Proximal Point Algorithm with Momentum","created":"2021-11-11","cited_by_count":7,"area":null},{"id":"2208.05287","title":"Adaptive Learning Rates for Faster Stochastic Gradient Methods","created":"2022-08-10","cited_by_count":7,"area":null},{"id":"2212.07282","title":"Low-Variance Forward Gradients using Direct Feedback Alignment and Momentum","created":"2022-12-14","cited_by_count":7,"area":null},{"id":"2302.12717","title":"Statistical Inference with Stochastic Gradient Methods under $\\phi$-mixing Data","created":"2023-02-24","cited_by_count":7,"area":null},{"id":"2303.01370","title":"Non asymptotic analysis of Adaptive stochastic gradient algorithms and applications","created":"2023-03-01","cited_by_count":7,"area":null},{"id":"2401.09339","title":"Central Limit Theorem for Two-Timescale Stochastic Approximation with Markovian Noise: Theory and Applications","created":"2024-01-17","cited_by_count":7,"area":null},{"id":"2409.04707","title":"Enhancing Deep Learning with Optimized Gradient Descent: Bridging Numerical Methods and Neural Network Training","created":"2024-09-07","cited_by_count":7,"area":null},{"id":"2504.10018","title":"RGB-Event based Pedestrian Attribute Recognition: A Benchmark Dataset and An Asymmetric RWKV Fusion Framework","created":"2025-04-14","cited_by_count":7,"area":null},{"id":"2109.01806","title":"On Faster Convergence of Scaled Sign Gradient Descent","created":"2021-09-04","cited_by_count":6,"area":null},{"id":"2206.01991","title":"Constructing unbiased gradient estimators with finite variance for conditional stochastic optimization","created":"2022-06-04","cited_by_count":6,"area":null},{"id":"2208.11246","title":"Accelerating SGD for Highly Ill-Conditioned Huge-Scale Online Matrix Completion","created":"2022-08-24","cited_by_count":6,"area":null},{"id":"2209.05148","title":"Personalized Federated Learning with Communication Compression","created":"2022-09-12","cited_by_count":6,"area":null},{"id":"2209.07446","title":"Efficiency Ordering of Stochastic Gradient Descent","created":"2022-09-15","cited_by_count":6,"area":null},{"id":"2209.07883","title":"Minibatch Stochastic Three Points Method for Unconstrained Smooth Minimization","created":"2022-09-16","cited_by_count":6,"area":null},{"id":"2211.03241","title":"Neural PDE Solvers for Irregular Domains","created":"2022-11-07","cited_by_count":6,"area":null},{"id":"2303.10472","title":"Practical and Matching Gradient Variance Bounds for Black-Box Variational Bayesian Inference","created":"2023-03-18","cited_by_count":6,"area":null},{"id":"2306.16484","title":"Towards a Better Theoretical Understanding of Independent Subnetwork Training","created":"2023-06-28","cited_by_count":6,"area":null},{"id":"2410.04285","title":"MindFlayer SGD: Efficient Parallel SGD in the Presence of Heterogeneous and Random Worker Compute Times","created":"2024-10-05","cited_by_count":6,"area":null},{"id":"2109.07117","title":"Non-Asymptotic Analysis of Stochastic Approximation Algorithms for Streaming Data","created":"2021-09-15","cited_by_count":5,"area":null},{"id":"2305.13170","title":"Explicit Personalization and Local Training: Double Communication Acceleration in Federated Learning","created":"2023-05-22","cited_by_count":5,"area":null},{"id":"2309.02082","title":"Backward error analysis and the qualitative behaviour of stochastic optimization algorithms: Application to stochastic coordinate descent","created":"2023-09-05","cited_by_count":5,"area":null},{"id":"2403.07148","title":"Stochastic Extragradient with Random Reshuffling: Improved Convergence for Variational Inequalities","created":"2024-03-11","cited_by_count":5,"area":null},{"id":"2501.08263","title":"Multiplayer Federated Learning: Reaching Equilibrium with Less Communication","created":"2025-01-14","cited_by_count":5,"area":null},{"id":"2504.01898","title":"Analysis of an Idealized Stochastic Polyak Method and its Application to Black-Box Model Distillation","created":"2025-04-02","cited_by_count":5,"area":null},{"id":"2509.22860","title":"Ringleader ASGD: The First Asynchronous SGD with Optimal Time Complexity under Data Heterogeneity","created":"2025-09-26","cited_by_count":5,"area":null},{"id":"2105.11818","title":"SGD with Coordinate Sampling: Theory and Practice","created":"2021-05-25","cited_by_count":4,"area":null},{"id":"2110.10093","title":"Stochastic Primal-Dual Deep Unrolling","created":"2021-10-19","cited_by_count":4,"area":null},{"id":"2203.02383","title":"Distributed Methods with Absolute Compression and Error Compensation","created":"2022-03-04","cited_by_count":4,"area":null},{"id":"2205.10864","title":"Federated Learning Aggregation: New Robust Algorithms with Guarantees","created":"2022-05-22","cited_by_count":4,"area":null},{"id":"2301.12677","title":"Distributed Stochastic Optimization under a General Variance Condition","created":"2023-01-30","cited_by_count":4,"area":null}],"next_cursor":"100"}