{"total":575,"rows":[{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019,"area":null},{"id":"2103.03279","title":"Remember What You Want to Forget: Algorithms for Machine Unlearning","created":"2021-03-04","cited_by_count":371,"area":"safety"},{"id":"2601.20802","title":"Reinforcement Learning via Self-Distillation","created":"2026-01-28","cited_by_count":332,"area":"lr"},{"id":"2312.00886","title":"Nash Learning from Human Feedback","created":"2023-12-01","cited_by_count":224,"area":"alignment"},{"id":"2108.10252","title":"Federated Multi-Task Learning under a Mixture of Distributions","created":"2021-08-23","cited_by_count":192,"area":null},{"id":"2404.03715","title":"Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences","created":"2024-04-04","cited_by_count":178,"area":"alignment"},{"id":"2210.06718","title":"Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient","created":"2022-10-13","cited_by_count":161,"area":null},{"id":"2105.14368","title":"Fit without fear: remarkable mathematical phenomena of deep learning through the prism of interpolation","created":"2021-05-29","cited_by_count":132,"area":null},{"id":"2102.07053","title":"Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradients","created":"2021-02-14","cited_by_count":123,"area":null},{"id":"2106.01969","title":"Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games","created":"2021-06-03","cited_by_count":93,"area":null},{"id":"2108.06924","title":"Near-Optimal No-Regret Learning in General Games","created":"2021-08-16","cited_by_count":85,"area":null},{"id":"2202.00665","title":"Tutorial on amortized optimization","created":"2022-02-01","cited_by_count":83,"area":null},{"id":"2106.10874","title":"FedCM: Federated Learning with Client-level Momentum","created":"2021-06-21","cited_by_count":77,"area":null},{"id":"2310.10616","title":"How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations","created":"2023-10-16","cited_by_count":75,"area":null},{"id":"2202.06386","title":"Improved analysis for a proximal algorithm for sampling","created":"2022-02-13","cited_by_count":73,"area":null},{"id":"2102.11845","title":"Learning with User-Level Privacy","created":"2021-02-23","cited_by_count":72,"area":null},{"id":"2107.13541","title":"Towards Robustness Against Natural Language Word Substitutions","created":"2021-07-28","cited_by_count":69,"area":null},{"id":"2105.11144","title":"Improved OOD Generalization via Adversarial Training and Pre-training","created":"2021-05-24","cited_by_count":66,"area":null},{"id":"2206.05825","title":"A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games","created":"2022-06-12","cited_by_count":66,"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":"2402.10500","title":"Active Preference Optimization for Sample Efficient RLHF","created":"2024-02-16","cited_by_count":62,"area":"alignment"},{"id":"2205.13710","title":"Privacy of Noisy Stochastic Gradient Descent: More Iterations without More Privacy Loss","created":"2022-05-27","cited_by_count":61,"area":null},{"id":"2404.14743","title":"Gradient Guidance for Diffusion Models: An Optimization Perspective","created":"2024-04-23","cited_by_count":61,"area":"diffusion"},{"id":"2103.06064","title":"Graph Neural Networks Inspired by Classical Iterative Algorithms","created":"2021-03-10","cited_by_count":60,"area":null},{"id":"2101.06905","title":"Blockchain Assisted Decentralized Federated Learning (BLADE-FL): Performance Analysis and Resource Allocation","created":"2021-01-18","cited_by_count":56,"area":null},{"id":"2106.03787","title":"Concave Utility Reinforcement Learning: the Mean-Field Game Viewpoint","created":"2021-06-07","cited_by_count":56,"area":null},{"id":"2108.08842","title":"EDEN: Communication-Efficient and Robust Distributed Mean Estimation for Federated Learning","created":"2021-08-19","cited_by_count":55,"area":null},{"id":"2205.06900","title":"MM-BD: Post-Training Detection of Backdoor Attacks with Arbitrary Backdoor Pattern Types Using a Maximum Margin Statistic","created":"2022-05-13","cited_by_count":55,"area":null},{"id":"2306.00204","title":"Toward Understanding Why Adam Converges Faster Than SGD for Transformers","created":"2023-05-31","cited_by_count":53,"area":null},{"id":"2103.10481","title":"Semi-Decentralized Federated Learning with Cooperative D2D Local Model Aggregations","created":"2021-03-18","cited_by_count":51,"area":null},{"id":"2309.01753","title":"On Penalty Methods for Nonconvex Bilevel Optimization and First-Order Stochastic Approximation","created":"2023-09-04","cited_by_count":51,"area":null},{"id":"2205.02160","title":"Making SGD Parameter-Free","created":"2022-05-04","cited_by_count":50,"area":null},{"id":"2106.01336","title":"Improved Rates for Differentially Private Stochastic Convex Optimization with Heavy-Tailed Data","created":"2021-06-02","cited_by_count":47,"area":null},{"id":"2406.09405","title":"Why Warmup the Learning Rate? Underlying Mechanisms and Improvements","created":"2024-06-13","cited_by_count":46,"area":null},{"id":"2302.03775","title":"Optimal Stochastic Non-smooth Non-convex Optimization through Online-to-Non-convex Conversion","created":"2023-02-07","cited_by_count":45,"area":null},{"id":"2105.06072","title":"Leveraging Non-uniformity in First-order Non-convex Optimization","created":"2021-05-13","cited_by_count":44,"area":null},{"id":"2103.12024","title":"Stability and Deviation Optimal Risk Bounds with Convergence Rate $O(1/n)$","created":"2021-03-22","cited_by_count":42,"area":null},{"id":"2110.05682","title":"Provably Efficient Reinforcement Learning in Decentralized General-Sum Markov Games","created":"2021-10-12","cited_by_count":42,"area":null},{"id":"2302.06570","title":"Beyond Uniform Smoothness: A Stopped Analysis of Adaptive SGD","created":"2023-02-13","cited_by_count":41,"area":null},{"id":"2104.11824","title":"Optimal Dynamic Regret in Exp-Concave Online Learning","created":"2021-04-23","cited_by_count":40,"area":null},{"id":"2302.02774","title":"The SSL Interplay: Augmentations, Inductive Bias, and Generalization","created":"2023-02-06","cited_by_count":40,"area":null},{"id":"2103.15209","title":"Understanding the role of importance weighting for deep learning","created":"2021-03-28","cited_by_count":39,"area":null},{"id":"2207.04036","title":"Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent","created":"2022-07-08","cited_by_count":39,"area":null},{"id":"2305.00241","title":"When Deep Learning Meets Polyhedral Theory: A Survey","created":"2023-04-29","cited_by_count":39,"area":null},{"id":"2102.01117","title":"SGD Generalizes Better Than GD (And Regularization Doesn't Help)","created":"2021-02-01","cited_by_count":38,"area":null},{"id":"2302.14428","title":"Stochastic Gradient Descent under Markovian Sampling Schemes","created":"2023-02-28","cited_by_count":38,"area":null},{"id":"2307.05014","title":"Test-Time Training on Video Streams","created":"2023-07-11","cited_by_count":37,"area":null},{"id":"2305.16284","title":"DoWG Unleashed: An Efficient Universal Parameter-Free Gradient Descent Method","created":"2023-05-25","cited_by_count":35,"area":null},{"id":"2306.13253","title":"Predicting Grokking Long Before it Happens: A look into the loss landscape of models which grok","created":"2023-06-23","cited_by_count":35,"area":null},{"id":"2303.08059","title":"Fast Rates for Maximum Entropy Exploration","created":"2023-03-14","cited_by_count":33,"area":null},{"id":"2106.08502","title":"Averaging on the Bures-Wasserstein manifold: dimension-free convergence of gradient descent","created":"2021-06-16","cited_by_count":32,"area":null},{"id":"2204.04452","title":"Refined Convergence and Topology Learning for Decentralized SGD with Heterogeneous Data","created":"2022-04-09","cited_by_count":32,"area":null},{"id":"2112.09745","title":"Interpretable Data-Based Explanations for Fairness Debugging","created":"2021-12-17","cited_by_count":30,"area":null},{"id":"2205.11765","title":"Byzantine-Robust Federated Learning with Optimal Statistical Rates and Privacy Guarantees","created":"2022-05-24","cited_by_count":30,"area":null},{"id":"2206.00159","title":"Provably Efficient Offline Multi-agent Reinforcement Learning via Strategy-wise Bonus","created":"2022-06-01","cited_by_count":30,"area":"offlinerl"},{"id":"2301.13139","title":"A Novel Framework for Policy Mirror Descent with General Parameterization and Linear Convergence","created":"2023-01-30","cited_by_count":30,"area":null},{"id":"2212.06325","title":"AFLGuard: Byzantine-robust Asynchronous Federated Learning","created":"2022-12-13","cited_by_count":29,"area":null},{"id":"2306.05131","title":"Conformal Prediction for Federated Uncertainty Quantification Under Label Shift","created":"2023-06-08","cited_by_count":29,"area":null},{"id":"2506.20520","title":"Asymmetric REINFORCE for off-Policy Reinforcement Learning: Balancing positive and negative rewards","created":"2025-06-25","cited_by_count":29,"area":"lr"},{"id":"2103.11003","title":"Differentially private inference via noisy optimization","created":"2021-03-19","cited_by_count":27,"area":null},{"id":"2106.06788","title":"Learngene: From Open-World to Your Learning Task","created":"2021-06-12","cited_by_count":27,"area":null},{"id":"2301.01766","title":"Learning Gaussian Mixtures Using the Wasserstein-Fisher-Rao Gradient Flow","created":"2023-01-04","cited_by_count":27,"area":null},{"id":"2509.26287","title":"Flower: A Flow-Matching Solver for Inverse Problems","created":"2025-09-30","cited_by_count":27,"area":"diffusion"},{"id":"2110.11876","title":"Tight and Robust Private Mean Estimation with Few Users","created":"2021-10-22","cited_by_count":26,"area":null},{"id":"2203.06735","title":"Private Non-Convex Federated Learning Without a Trusted Server","created":"2022-03-13","cited_by_count":26,"area":null},{"id":"2205.12808","title":"Mirror Descent Maximizes Generalized Margin and Can Be Implemented Efficiently","created":"2022-05-25","cited_by_count":26,"area":null},{"id":"2106.09481","title":"Stochastic Bias-Reduced Gradient Methods","created":"2021-06-17","cited_by_count":25,"area":null},{"id":"2206.08742","title":"Near-Optimal No-Regret Learning Dynamics for General Convex Games","created":"2022-06-17","cited_by_count":25,"area":null},{"id":"2406.18060","title":"AdaZeta: Adaptive Zeroth-Order Tensor-Train Adaption for Memory-Efficient Large Language Models Fine-Tuning","created":"2024-06-26","cited_by_count":25,"area":null},{"id":"2507.20016","title":"FedSWA: Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight Averaging","created":"2025-07-26","cited_by_count":25,"area":null},{"id":"2202.11632","title":"Mirror Descent Strikes Again: Optimal Stochastic Convex Optimization under Infinite Noise Variance","created":"2022-02-23","cited_by_count":24,"area":null},{"id":"2405.19544","title":"One-Shot Safety Alignment for Large Language Models via Optimal Dualization","created":"2024-05-29","cited_by_count":24,"area":"alignment"},{"id":"2410.10373","title":"Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late in Training","created":"2024-10-14","cited_by_count":24,"area":null},{"id":"2107.10110","title":"On the Convergence of Prior-Guided Zeroth-Order Optimization Algorithms","created":"2021-07-21","cited_by_count":23,"area":null},{"id":"2111.00552","title":"Policy Optimization for Constrained MDPs with Provable Fast Global Convergence","created":"2021-10-31","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":"2210.08448","title":"Resolving the Mixing Time of the Langevin Algorithm to its Stationary Distribution for Log-Concave Sampling","created":"2022-10-16","cited_by_count":22,"area":null},{"id":"2303.07160","title":"Tighter Lower Bounds for Shuffling SGD: Random Permutations and Beyond","created":"2023-03-13","cited_by_count":22,"area":null},{"id":"1901.03674","title":"On the Global Convergence of Imitation Learning: A Case for Linear Quadratic Regulator","created":"2019-01-11","cited_by_count":21,"area":"offlinerl"},{"id":"2202.04598","title":"Reproducibility in Optimization: Theoretical Framework and Limits","created":"2022-02-09","cited_by_count":21,"area":null},{"id":"2401.15866","title":"Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attribution","created":"2024-01-29","cited_by_count":21,"area":null},{"id":"2406.19827","title":"Towards Stable and Storage-efficient Dataset Distillation: Matching Convexified Trajectory","created":"2024-06-28","cited_by_count":21,"area":null},{"id":"2102.06333","title":"Efficient Algorithms for Federated Saddle Point Optimization","created":"2021-02-12","cited_by_count":20,"area":null},{"id":"2111.11309","title":"No-Regret Dynamics in the Fenchel Game: A Unified Framework for Algorithmic Convex Optimization","created":"2021-11-22","cited_by_count":20,"area":null},{"id":"2212.07356","title":"Scheduling and Aggregation Design for Asynchronous Federated Learning over Wireless Networks","created":"2022-12-14","cited_by_count":20,"area":null},{"id":"2305.15572","title":"The Behavior and Convergence of Local Bayesian Optimization","created":"2023-05-24","cited_by_count":20,"area":null},{"id":"2306.09850","title":"Practical Sharpness-Aware Minimization Cannot Converge All the Way to Optima","created":"2023-06-16","cited_by_count":20,"area":null},{"id":"2312.02849","title":"Algorithms for mean-field variational inference via polyhedral optimization in the Wasserstein space","created":"2023-12-05","cited_by_count":20,"area":null},{"id":"2406.07529","title":"MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation","created":"2024-06-11","cited_by_count":20,"area":null},{"id":"2109.05439","title":"Concave Utility Reinforcement Learning with Zero-Constraint Violations","created":"2021-09-12","cited_by_count":19,"area":null},{"id":"2202.13361","title":"Benign Underfitting of Stochastic Gradient Descent","created":"2022-02-27","cited_by_count":19,"area":null},{"id":"2204.11144","title":"Competitive Physics Informed Networks","created":"2022-04-23","cited_by_count":19,"area":null},{"id":"2212.13556","title":"Limitations of Information-Theoretic Generalization Bounds for Gradient Descent Methods in Stochastic Convex Optimization","created":"2022-12-27","cited_by_count":19,"area":null},{"id":"2102.11055","title":"Escaping from Zero Gradient: Revisiting Action-Constrained Reinforcement Learning via Frank-Wolfe Policy Optimization","created":"2021-02-22","cited_by_count":18,"area":null},{"id":"2105.14163","title":"The query complexity of sampling from strongly log-concave distributions in one dimension","created":"2021-05-29","cited_by_count":18,"area":null},{"id":"2108.05828","title":"A general class of surrogate functions for stable and efficient reinforcement learning","created":"2021-08-12","cited_by_count":18,"area":null},{"id":"2302.11381","title":"Optimal Convergence Rate for Exact Policy Mirror Descent in Discounted Markov Decision Processes","created":"2023-02-22","cited_by_count":18,"area":null},{"id":"2102.09718","title":"Permutation-Based SGD: Is Random Optimal?","created":"2021-02-19","cited_by_count":17,"area":null},{"id":"2105.01778","title":"Thinking Inside the Ball: Near-Optimal Minimization of the Maximal Loss","created":"2021-05-04","cited_by_count":17,"area":null},{"id":"2106.01101","title":"Learning a Single Neuron with Bias Using Gradient Descent","created":"2021-06-02","cited_by_count":17,"area":null}],"next_cursor":"100"}