{"total":665,"rows":[{"id":"2101.11203","title":"Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learning","created":"2021-01-27","cited_by_count":193,"area":null},{"id":"2109.00650","title":"Dash: Semi-Supervised Learning with Dynamic Thresholding","created":"2021-09-01","cited_by_count":148,"area":null},{"id":"2206.06232","title":"Towards Understanding Sharpness-Aware Minimization","created":"2022-06-13","cited_by_count":146,"area":null},{"id":"2104.11375","title":"Decentralized Federated Averaging","created":"2021-04-23","cited_by_count":114,"area":null},{"id":"2402.11592","title":"Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark","created":"2024-02-18","cited_by_count":114,"area":null},{"id":"2201.13409","title":"A framework for bilevel optimization that enables stochastic and global variance reduction algorithms","created":"2022-01-31","cited_by_count":99,"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":"2202.00817","title":"Do Differentiable Simulators Give Better Policy Gradients?","created":"2022-02-02","cited_by_count":89,"area":null},{"id":"2206.07136","title":"Automatic Clipping: Differentially Private Deep Learning Made Easier and Stronger","created":"2022-06-14","cited_by_count":88,"area":null},{"id":"2305.01588","title":"Revisiting Gradient Clipping: Stochastic bias and tight convergence guarantees","created":"2023-05-02","cited_by_count":83,"area":null},{"id":"2208.11195","title":"Robustness to Unbounded Smoothness of Generalized SignSGD","created":"2022-08-23","cited_by_count":81,"area":null},{"id":"2106.14343","title":"High-probability Bounds for Non-Convex Stochastic Optimization with Heavy Tails","created":"2021-06-28","cited_by_count":80,"area":null},{"id":"2206.08307","title":"Sharper Convergence Guarantees for Asynchronous SGD for Distributed and Federated Learning","created":"2022-06-16","cited_by_count":79,"area":null},{"id":"2107.11433","title":"A general sample complexity analysis of vanilla policy gradient","created":"2021-07-23","cited_by_count":76,"area":null},{"id":"2310.02025","title":"DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training","created":"2023-10-03","cited_by_count":76,"area":null},{"id":"2102.11845","title":"Learning with User-Level Privacy","created":"2021-02-23","cited_by_count":72,"area":null},{"id":"2210.05177","title":"Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach","created":"2022-10-11","cited_by_count":70,"area":null},{"id":"2102.04671","title":"A Single-Timescale Method for Stochastic Bilevel Optimization","created":"2021-02-09","cited_by_count":69,"area":null},{"id":"2205.05878","title":"Training Uncertainty-Aware Classifiers with Conformalized Deep Learning","created":"2022-05-12","cited_by_count":64,"area":null},{"id":"2411.10438","title":"MARS: Unleashing the Power of Variance Reduction for Training Large Models","created":"2024-11-15","cited_by_count":64,"area":null},{"id":"2205.12173","title":"Byzantine Machine Learning Made Easy by Resilient Averaging of Momentums","created":"2022-05-24","cited_by_count":63,"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":"2202.05791","title":"The Power of Adaptivity in SGD: Self-Tuning Step Sizes with Unbounded Gradients and Affine Variance","created":"2022-02-11","cited_by_count":61,"area":null},{"id":"2205.02215","title":"FedNest: Federated Bilevel, Minimax, and Compositional Optimization","created":"2022-05-04","cited_by_count":60,"area":null},{"id":"2201.09531","title":"Communication-Efficient Stochastic Zeroth-Order Optimization for Federated Learning","created":"2022-01-24","cited_by_count":59,"area":null},{"id":"2302.01734","title":"Stochastic Policy Gradient Methods: Improved Sample Complexity for Fisher-non-degenerate Policies","created":"2023-02-03","cited_by_count":58,"area":null},{"id":"2404.08080","title":"Variance-reduced Zeroth-Order Methods for Fine-Tuning Language Models","created":"2024-04-11","cited_by_count":54,"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":"2402.15173","title":"Second-Order Fine-Tuning without Pain for LLMs:A Hessian Informed Zeroth-Order Optimizer","created":"2024-02-23","cited_by_count":53,"area":null},{"id":"2403.12350","title":"Friendly Sharpness-Aware Minimization","created":"2024-03-19","cited_by_count":53,"area":null},{"id":"2410.07698","title":"Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank Structures","created":"2024-10-10","cited_by_count":50,"area":null},{"id":"2410.13849","title":"From Gradient Clipping to Normalization for Heavy Tailed SGD","created":"2024-10-17","cited_by_count":49,"area":null},{"id":"2402.11867","title":"LoRA Training in the NTK Regime has No Spurious Local Minima","created":"2024-02-19","cited_by_count":48,"area":null},{"id":"2102.10707","title":"A Zeroth-Order Block Coordinate Descent Algorithm for Huge-Scale Black-Box Optimization","created":"2021-02-21","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":"2302.04083","title":"Improving the Model Consistency of Decentralized Federated Learning","created":"2023-02-08","cited_by_count":45,"area":null},{"id":"2306.01244","title":"Towards Sustainable Learning: Coresets for Data-efficient Deep Learning","created":"2023-06-02","cited_by_count":44,"area":null},{"id":"2306.01264","title":"Convex and Non-convex Optimization Under Generalized Smoothness","created":"2023-06-02","cited_by_count":44,"area":null},{"id":"2209.05045","title":"Gradient-Free Methods for Deterministic and Stochastic Nonsmooth Nonconvex Optimization","created":"2022-09-12","cited_by_count":43,"area":null},{"id":"2304.14647","title":"An Adaptive Policy to Employ Sharpness-Aware Minimization","created":"2023-04-28","cited_by_count":43,"area":null},{"id":"2108.09875","title":"Anarchic Federated Learning","created":"2021-08-23","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":"2308.00788","title":"An Introduction to Bi-level Optimization: Foundations and Applications in Signal Processing and Machine Learning","created":"2023-08-01","cited_by_count":41,"area":null},{"id":"2401.04343","title":"Private Fine-tuning of Large Language Models with Zeroth-order Optimization","created":"2024-01-09","cited_by_count":41,"area":null},{"id":"2106.08208","title":"SUPER-ADAM: Faster and Universal Framework of Adaptive Gradients","created":"2021-06-15","cited_by_count":40,"area":null},{"id":"2204.02833","title":"High Probability Bounds for a Class of Nonconvex Algorithms with AdaGrad Stepsize","created":"2022-04-06","cited_by_count":40,"area":null},{"id":"2104.06763","title":"Oracle Complexity in Nonsmooth Nonconvex Optimization","created":"2021-04-14","cited_by_count":39,"area":null},{"id":"2105.01650","title":"Stochastic gradient descent with noise of machine learning type. Part I: Discrete time analysis","created":"2021-05-04","cited_by_count":39,"area":null},{"id":"2110.12459","title":"Non-convex Distributionally Robust Optimization: Non-asymptotic Analysis","created":"2021-10-24","cited_by_count":39,"area":null},{"id":"2203.14195","title":"How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective","created":"2022-03-27","cited_by_count":39,"area":null},{"id":"2203.06560","title":"Query-Efficient Black-box Adversarial Attacks Guided by a Transfer-based Prior","created":"2022-03-13","cited_by_count":38,"area":null},{"id":"2310.17998","title":"Closing the Gap Between the Upper Bound and the Lower Bound of Adam's Iteration Complexity","created":"2023-10-27","cited_by_count":38,"area":null},{"id":"2102.06489","title":"Stability and Convergence of Stochastic Gradient Clipping: Beyond Lipschitz Continuity and Smoothness","created":"2021-02-12","cited_by_count":37,"area":null},{"id":"2309.15639","title":"Enhancing Sharpness-Aware Optimization Through Variance Suppression","created":"2023-09-27","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":"2110.05707","title":"On Improving Model-Free Algorithms for Decentralized Multi-Agent Reinforcement Learning","created":"2021-10-12","cited_by_count":36,"area":null},{"id":"2111.12292","title":"Improved Fine-Tuning by Better Leveraging Pre-Training Data","created":"2021-11-24","cited_by_count":36,"area":null},{"id":"2202.04428","title":"Adapting to Mixing Time in Stochastic Optimization with Markovian Data","created":"2022-02-09","cited_by_count":36,"area":null},{"id":"2206.13033","title":"Normalized/Clipped SGD with Perturbation for Differentially Private Non-Convex Optimization","created":"2022-06-27","cited_by_count":36,"area":null},{"id":"2405.16002","title":"Does SGD really happen in tiny subspaces?","created":"2024-05-25","cited_by_count":36,"area":null},{"id":"2601.19156","title":"Convergence of Muon with Newton-Schulz","created":"2026-01-27","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":"2110.07004","title":"On the Convergence Theory for Hessian-Free Bilevel Algorithms","created":"2021-10-13","cited_by_count":35,"area":null},{"id":"2202.04295","title":"On Almost Sure Convergence Rates of Stochastic Gradient Methods","created":"2022-02-09","cited_by_count":35,"area":null},{"id":"2206.09888","title":"SoteriaFL: A Unified Framework for Private Federated Learning with Communication Compression","created":"2022-06-20","cited_by_count":34,"area":null},{"id":"2303.11242","title":"Make Landscape Flatter in Differentially Private Federated Learning","created":"2023-03-20","cited_by_count":33,"area":null},{"id":"2106.11879","title":"Asynchronous Stochastic Optimization Robust to Arbitrary Delays","created":"2021-06-22","cited_by_count":32,"area":null},{"id":"2206.00846","title":"Faster Rates of Convergence to Stationary Points in Differentially Private Optimization","created":"2022-06-02","cited_by_count":32,"area":null},{"id":"2208.09900","title":"Provable Adaptivity of Adam under Non-uniform Smoothness","created":"2022-08-21","cited_by_count":30,"area":null},{"id":"2302.08783","title":"SGD with AdaGrad Stepsizes: Full Adaptivity with High Probability to Unknown Parameters, Unbounded Gradients and Affine Variance","created":"2023-02-17","cited_by_count":30,"area":null},{"id":"2103.01447","title":"ZeroSARAH: Efficient Nonconvex Finite-Sum Optimization with Zero Full Gradient Computation","created":"2021-03-02","cited_by_count":29,"area":null},{"id":"2311.03252","title":"Parameter-Agnostic Optimization under Relaxed Smoothness","created":"2023-11-06","cited_by_count":29,"area":null},{"id":"2302.06763","title":"Breaking the Lower Bound with (Little) Structure: Acceleration in Non-Convex Stochastic Optimization with Heavy-Tailed Noise","created":"2023-02-14","cited_by_count":27,"area":null},{"id":"2510.19933","title":"Beyond the Ideal: Analyzing the Inexact Muon Update","created":"2025-10-22","cited_by_count":27,"area":null},{"id":"2302.08300","title":"Deterministic Nonsmooth Nonconvex Optimization","created":"2023-02-16","cited_by_count":26,"area":null},{"id":"2310.09639","title":"DPZero: Private Fine-Tuning of Language Models without Backpropagation","created":"2023-10-14","cited_by_count":26,"area":null},{"id":"2206.07082","title":"Stability and Generalization of Stochastic Optimization with Nonconvex and Nonsmooth Problems","created":"2022-06-14","cited_by_count":25,"area":null},{"id":"2312.15184","title":"ZO-AdaMU Optimizer: Adapting Perturbation by the Momentum and Uncertainty in Zeroth-order Optimization","created":"2023-12-23","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":"2305.12475","title":"Two Sides of One Coin: the Limits of Untuned SGD and the Power of Adaptive Methods","created":"2023-05-21","cited_by_count":23,"area":null},{"id":"2307.04504","title":"An Algorithm with Optimal Dimension-Dependence for Zero-Order Nonsmooth Nonconvex Stochastic Optimization","created":"2023-07-10","cited_by_count":23,"area":null},{"id":"2106.13781","title":"Tighter Analysis of Alternating Stochastic Gradient Method for Stochastic Nested Problems","created":"2021-06-25","cited_by_count":22,"area":null},{"id":"2202.12183","title":"Large-scale Stochastic Optimization of NDCG Surrogates for Deep Learning with Provable Convergence","created":"2022-02-24","cited_by_count":22,"area":null},{"id":"2304.01541","title":"Privacy Amplification via Compression: Achieving the Optimal Privacy-Accuracy-Communication Trade-off in Distributed Mean Estimation","created":"2023-04-04","cited_by_count":22,"area":null},{"id":"2406.15244","title":"AdaGrad under Anisotropic Smoothness","created":"2024-06-21","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":"2110.14807","title":"L2ight: Enabling On-Chip Learning for Optical Neural Networks via Efficient in-situ Subspace Optimization","created":"2021-10-27","cited_by_count":21,"area":null},{"id":"2202.01666","title":"Proportional Fairness in Federated Learning","created":"2022-02-03","cited_by_count":21,"area":null},{"id":"2202.07554","title":"Between Stochastic and Adversarial Online Convex Optimization: Improved Regret Bounds via Smoothness","created":"2022-02-15","cited_by_count":21,"area":null},{"id":"2206.09491","title":"On the Limitations of Stochastic Pre-processing Defenses","created":"2022-06-19","cited_by_count":21,"area":null},{"id":"2210.14026","title":"SWIFT: Rapid Decentralized Federated Learning via Wait-Free Model Communication","created":"2022-10-25","cited_by_count":21,"area":null},{"id":"2212.00328","title":"Differentially Private Learning with Per-Sample Adaptive Clipping","created":"2022-12-01","cited_by_count":21,"area":null},{"id":"2302.09029","title":"Solving stochastic weak Minty variational inequalities without increasing batch size","created":"2023-02-17","cited_by_count":21,"area":null},{"id":"2310.01972","title":"Epidemic Learning: Boosting Decentralized Learning with Randomized Communication","created":"2023-10-03","cited_by_count":21,"area":null},{"id":"2402.03982","title":"On Convergence of Adam for Stochastic Optimization under Relaxed Assumptions","created":"2024-02-06","cited_by_count":21,"area":null},{"id":"2111.12050","title":"Simple Stochastic and Online Gradient Descent Algorithms for Pairwise Learning","created":"2021-11-23","cited_by_count":20,"area":null},{"id":"2205.05040","title":"A Communication-Efficient Distributed Gradient Clipping Algorithm for Training Deep Neural Networks","created":"2022-05-10","cited_by_count":20,"area":null},{"id":"2207.00391","title":"A Theoretical Analysis of the Learning Dynamics under Class Imbalance","created":"2022-07-01","cited_by_count":20,"area":null},{"id":"2306.00144","title":"Mechanic: A Learning Rate Tuner","created":"2023-05-31","cited_by_count":20,"area":null},{"id":"2405.06979","title":"Robust Semi-supervised Learning by Wisely Leveraging Open-set Data","created":"2024-05-11","cited_by_count":20,"area":null}],"next_cursor":"100"}