{"total":116,"rows":[{"id":"2103.00065","title":"Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability","created":"2021-02-26","cited_by_count":427,"area":null},{"id":"2302.12022","title":"DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule","created":"2023-02-08","cited_by_count":85,"area":null},{"id":"2205.02160","title":"Making SGD Parameter-Free","created":"2022-05-04","cited_by_count":50,"area":null},{"id":"2102.03183","title":"Last iterate convergence of SGD for Least-Squares in the Interpolation regime","created":"2021-02-05","cited_by_count":42,"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":"2102.05320","title":"An Adaptive Stochastic Sequential Quadratic Programming with Differentiable Exact Augmented Lagrangians","created":"2021-02-10","cited_by_count":25,"area":null},{"id":"2305.07583","title":"MoMo: Momentum Models for Adaptive Learning Rates","created":"2023-05-12","cited_by_count":24,"area":null},{"id":"2308.06058","title":"Adaptive SGD with Polyak stepsize and Line-search: Robust Convergence and Variance Reduction","created":"2023-08-11","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":"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":"2106.11851","title":"Stochastic Polyak Stepsize with a Moving Target","created":"2021-06-22","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":"2110.11442","title":"Towards Noise-adaptive, Problem-adaptive (Accelerated) Stochastic Gradient Descent","created":"2021-10-21","cited_by_count":16,"area":null},{"id":"2206.00743","title":"Nest Your Adaptive Algorithm for Parameter-Agnostic Nonconvex Minimax Optimization","created":"2022-06-01","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":"2306.12747","title":"Don't be so Monotone: Relaxing Stochastic Line Search in Over-Parameterized Models","created":"2023-06-22","cited_by_count":15,"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":"2305.15938","title":"First Order Methods with Markovian Noise: from Acceleration to Variational Inequalities","created":"2023-05-25","cited_by_count":14,"area":null},{"id":"2102.09645","title":"SVRG Meets AdaGrad: Painless Variance Reduction","created":"2021-02-18","cited_by_count":13,"area":null},{"id":"2203.09670","title":"Latency Optimization for Blockchain-Empowered Federated Learning in Multi-Server Edge Computing","created":"2022-03-18","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":"2106.06338","title":"Understanding approximate and unrolled dictionary learning for pattern recovery","created":"2021-06-11","cited_by_count":11,"area":null},{"id":"2402.10898","title":"The Price of Adaptivity in Stochastic Convex Optimization","created":"2024-02-16","cited_by_count":11,"area":null},{"id":"2409.08770","title":"Increasing Both Batch Size and Learning Rate Accelerates Stochastic Gradient Descent","created":"2024-09-13","cited_by_count":11,"area":null},{"id":"2110.14432","title":"Iterative Teaching by Label Synthesis","created":"2021-10-27","cited_by_count":10,"area":null},{"id":"2207.03060","title":"Multi-Label Learning to Rank through Multi-Objective Optimization","created":"2022-07-07","cited_by_count":10,"area":null},{"id":"2405.14402","title":"Exact Gauss-Newton Optimization for Training Deep Neural Networks","created":"2024-05-23","cited_by_count":10,"area":null},{"id":"2109.02388","title":"On Second-order Optimization Methods for Federated Learning","created":"2021-09-06","cited_by_count":9,"area":null},{"id":"2203.00089","title":"Amortized Proximal Optimization","created":"2022-02-28","cited_by_count":9,"area":null},{"id":"2206.06900","title":"Grad-GradaGrad? A Non-Monotone Adaptive Stochastic Gradient Method","created":"2022-06-14","cited_by_count":9,"area":null},{"id":"2306.02527","title":"Searching for Optimal Per-Coordinate Step-sizes with Multidimensional Backtracking","created":"2023-06-05","cited_by_count":9,"area":null},{"id":"2312.14567","title":"Accelerated Convergence of Stochastic Heavy Ball Method under Anisotropic Gradient Noise","created":"2023-12-22","cited_by_count":9,"area":null},{"id":"2203.03159","title":"Risk Bounds of Multi-Pass SGD for Least Squares in the Interpolation Regime","created":"2022-03-07","cited_by_count":8,"area":null},{"id":"2210.17467","title":"Iterative Teaching by Data Hallucination","created":"2022-10-31","cited_by_count":8,"area":null},{"id":"2307.14528","title":"Function Value Learning: Adaptive Learning Rates Based on the Polyak Stepsize and Function Splitting in ERM","created":"2023-07-26","cited_by_count":8,"area":null},{"id":"2311.05788","title":"Structured Transforms Across Spaces with Cost-Regularized Optimal Transport","created":"2023-11-09","cited_by_count":8,"area":null},{"id":"2407.06183","title":"Stepping on the Edge: Curvature Aware Learning Rate Tuners","created":"2024-07-08","cited_by_count":8,"area":null},{"id":"2601.16979","title":"A Scalable Measure of Loss Landscape Curvature for Analyzing the Training Dynamics of LLMs","created":"2026-01-23","cited_by_count":8,"area":null},{"id":"2102.06604","title":"Cockpit: A Practical Debugging Tool for the Training of Deep Neural Networks","created":"2021-02-12","cited_by_count":7,"area":null},{"id":"2103.12293","title":"Stochastic Reweighted Gradient Descent","created":"2021-03-23","cited_by_count":7,"area":null},{"id":"2306.11201","title":"Adaptive Federated Learning with Auto-Tuned Clients","created":"2023-06-19","cited_by_count":7,"area":null},{"id":"2107.03331","title":"KOALA: A Kalman Optimization Algorithm with Loss Adaptivity","created":"2021-07-07","cited_by_count":6,"area":null},{"id":"2310.14085","title":"Adaptive, Doubly Optimal No-Regret Learning in Strongly Monotone and Exp-Concave Games with Gradient Feedback","created":"2023-10-21","cited_by_count":6,"area":null},{"id":"2402.02342","title":"MetaOptimize: A Framework for Optimizing Step Sizes and Other Meta-parameters","created":"2024-02-04","cited_by_count":5,"area":null},{"id":"2402.15344","title":"Iteration and Stochastic First-order Oracle Complexities of Stochastic Gradient Descent using Constant and Decaying Learning Rates","created":"2024-02-23","cited_by_count":5,"area":null},{"id":"2410.05140","title":"Tuning-Free Bilevel Optimization: New Algorithms and Convergence Analysis","created":"2024-10-07","cited_by_count":5,"area":null},{"id":"2502.09003","title":"RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models","created":"2025-02-13","cited_by_count":5,"area":null},{"id":"2205.12751","title":"Fast Stochastic Composite Minimization and an Accelerated Frank-Wolfe Algorithm under Parallelization","created":"2022-05-25","cited_by_count":4,"area":null},{"id":"2206.09908","title":"Learning Optimal Flows for Non-Equilibrium Importance Sampling","created":"2022-06-20","cited_by_count":4,"area":null},{"id":"2305.18666","title":"BiSLS/SPS: Auto-tune Step Sizes for Stable Bi-level Optimization","created":"2023-05-30","cited_by_count":4,"area":null},{"id":"2308.10098","title":"An adaptively inexact first-order method for bilevel optimization with application to hyperparameter learning","created":"2023-08-19","cited_by_count":4,"area":null},{"id":"2312.00209","title":"On the Interplay Between Stepsize Tuning and Progressive Sharpening","created":"2023-11-30","cited_by_count":4,"area":null},{"id":"2111.13162","title":"Randomized Stochastic Gradient Descent Ascent","created":"2021-11-25","cited_by_count":3,"area":null},{"id":"2201.12678","title":"A Stochastic Bundle Method for Interpolating Networks","created":"2022-01-29","cited_by_count":3,"area":null},{"id":"2405.19585","title":"The High Line: Exact Risk and Learning Rate Curves of Stochastic Adaptive Learning Rate Algorithms","created":"2024-05-30","cited_by_count":3,"area":null},{"id":"2503.00229","title":"Armijo Line-search Can Make (Stochastic) Gradient Descent Provably Faster","created":"2025-02-28","cited_by_count":3,"area":null},{"id":"2509.02970","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","created":"2025-09-03","cited_by_count":3,"area":null},{"id":"2103.17132","title":"Empirically explaining SGD from a line search perspective","created":"2021-03-31","cited_by_count":2,"area":null},{"id":"2203.16723","title":"Exploiting Explainable Metrics for Augmented SGD","created":"2022-03-31","cited_by_count":2,"area":null},{"id":"2403.07379","title":"Hallmarks of Optimization Trajectories in Neural Networks: Directional Exploration and Redundancy","created":"2024-03-12","cited_by_count":2,"area":null},{"id":"2408.03199","title":"Convergence Conditions for Stochastic Line Search Based Optimization of Over-parametrized Models","created":"2024-08-06","cited_by_count":2,"area":null},{"id":"2408.13150","title":"Adaptive Backtracking Line Search","created":"2024-08-23","cited_by_count":2,"area":null},{"id":"2412.19444","title":"Towards Simple and Provable Parameter-Free Adaptive Gradient Methods","created":"2024-12-27","cited_by_count":2,"area":null},{"id":"2505.21651","title":"AutoSGD: Automatic Learning Rate Selection for Stochastic Gradient Descent","created":"2025-05-27","cited_by_count":2,"area":null},{"id":"2506.12648","title":"Glocal Smoothness: Line search and adaptive step sizes can help in theory too!","created":"2025-06-14","cited_by_count":2,"area":null},{"id":"2512.02342","title":"Safeguarded Stochastic Polyak Step Sizes for Non-smooth Optimization: Robust Performance Without Small (Sub)Gradients","created":"2025-12-02","cited_by_count":2,"area":null},{"id":"2603.15059","title":"Muon Converges under Heavy-Tailed Noise: Nonconvex H\\\"{o}lder-Smooth Empirical Risk Minimization","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2112.13269","title":"Over-Parametrized Matrix Factorization in the Presence of Spurious Stationary Points","created":"2021-12-25","cited_by_count":1,"area":null},{"id":"2304.00459","title":"Fast Convergence of Random Reshuffling under Over-Parameterization and the Polyak-\\L ojasiewicz Condition","created":"2023-04-02","cited_by_count":1,"area":null},{"id":"2311.16956","title":"Adaptive Step Sizes for Preconditioned Stochastic Gradient Descent","created":"2023-11-28","cited_by_count":1,"area":null},{"id":"2403.03362","title":"Level Set Teleportation: An Optimization Perspective","created":"2024-03-05","cited_by_count":1,"area":null},{"id":"2403.18506","title":"Faster Convergence for Transformer Fine-tuning with Line Search Methods","created":"2024-03-27","cited_by_count":1,"area":null},{"id":"2403.18519","title":"Improving Line Search Methods for Large Scale Neural Network Training","created":"2024-03-27","cited_by_count":1,"area":null},{"id":"2406.17954","title":"Why Line Search when you can Plane Search? SO-Friendly Neural Networks allow Per-Iteration Optimization of Learning and Momentum Rates for Every Layer","created":"2024-06-25","cited_by_count":1,"area":null},{"id":"2407.20650","title":"No learning rates needed: Introducing SALSA -- Stable Armijo Line Search Adaptation","created":"2024-07-30","cited_by_count":1,"area":null},{"id":"2409.09984","title":"Convergence of Sharpness-Aware Minimization Algorithms using Increasing Batch Size and Decaying Learning Rate","created":"2024-09-16","cited_by_count":1,"area":null},{"id":"2411.07102","title":"Effectively Leveraging Momentum Terms in Stochastic Line Search Frameworks for Fast Optimization of Finite-Sum Problems","created":"2024-11-11","cited_by_count":1,"area":null},{"id":"2502.03701","title":"First-ish Order Methods: Hessian-aware Scalings of Gradient Descent","created":"2025-02-06","cited_by_count":1,"area":null},{"id":"2102.00853","title":"Painless step size adaptation for SGD","created":"2021-02-01","cited_by_count":0,"area":null},{"id":"2102.10880","title":"A Probabilistically Motivated Learning Rate Adaptation for Stochastic Optimization","created":"2021-02-22","cited_by_count":0,"area":null},{"id":"2104.02578","title":"Neurons learn slower than they think","created":"2021-04-02","cited_by_count":0,"area":null},{"id":"2104.12949","title":"Discriminative Bayesian filtering lends momentum to the stochastic Newton method for minimizing log-convex functions","created":"2021-04-27","cited_by_count":0,"area":null},{"id":"2106.06998","title":"XConv: Low-memory stochastic backpropagation for convolutional layers","created":"2021-06-13","cited_by_count":0,"area":null},{"id":"2106.08767","title":"To Raise or Not To Raise: The Autonomous Learning Rate Question","created":"2021-06-16","cited_by_count":0,"area":null},{"id":"2106.11548","title":"Adaptive Learning Rate and Momentum for Training Deep Neural Networks","created":"2021-06-22","cited_by_count":0,"area":null},{"id":"2108.13880","title":"Using a one dimensional parabolic model of the full-batch loss to estimate learning rates during training","created":"2021-08-31","cited_by_count":0,"area":null},{"id":"2110.00874","title":"Fast Line Search for Multi-Task Learning","created":"2021-10-02","cited_by_count":0,"area":null},{"id":"2111.07058","title":"Bolstering Stochastic Gradient Descent with Model Building","created":"2021-11-13","cited_by_count":0,"area":null},{"id":"2111.14056","title":"Towards Robust and Automatic Hyper-Parameter Tunning","created":"2021-11-28","cited_by_count":0,"area":null},{"id":"2204.01705","title":"Learning to Accelerate by the Methods of Step-size Planning","created":"2022-04-01","cited_by_count":0,"area":null},{"id":"2207.10046","title":"Adaptive Step-Size Methods for Compressed SGD","created":"2022-07-20","cited_by_count":0,"area":null},{"id":"2305.13664","title":"Layer-wise Adaptive Step-Sizes for Stochastic First-Order Methods for Deep Learning","created":"2023-05-23","cited_by_count":0,"area":null},{"id":"2306.10278","title":"Adaptive Strategies in Non-convex Optimization","created":"2023-06-17","cited_by_count":0,"area":null},{"id":"2307.13831","title":"Relationship between Batch Size and Number of Steps Needed for Nonconvex Optimization of Stochastic Gradient Descent using Armijo Line Search","created":"2023-07-25","cited_by_count":0,"area":null},{"id":"2308.08886","title":"Dual Gauss-Newton Directions for Deep Learning","created":"2023-08-17","cited_by_count":0,"area":null},{"id":"2309.01248","title":"Modified Step Size for Enhanced Stochastic Gradient Descent: Convergence and Experiments","created":"2023-09-03","cited_by_count":0,"area":null},{"id":"2311.13877","title":"Locally Optimal Descent for Dynamic Stepsize Scheduling","created":"2023-11-23","cited_by_count":0,"area":null},{"id":"2404.01257","title":"New logarithmic step size for stochastic gradient descent","created":"2024-04-01","cited_by_count":0,"area":null},{"id":"2404.02378","title":"Faster Convergence of Stochastic Accelerated Gradient Descent under Interpolation","created":"2024-04-03","cited_by_count":0,"area":null}],"next_cursor":"100"}