{"list":"other","total":52,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1708.04552","title":"Improved Regularization of Convolutional Neural Networks with Cutout","created":"2017-08-15","cited_by_count":1628},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"1609.04836","title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima","created":"2016-09-15","cited_by_count":1352},{"id":"1904.09237","title":"On the Convergence of Adam and Beyond","created":"2019-04-19","cited_by_count":841},{"id":"1706.08947","title":"Exploring Generalization in Deep Learning","created":"2017-06-27","cited_by_count":600},{"id":"1509.01240","title":"Train faster, generalize better: Stability of stochastic gradient descent","created":"2015-09-03","cited_by_count":552},{"id":"1608.04636","title":"Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-\\L{}ojasiewicz Condition","created":"2016-08-16","cited_by_count":539},{"id":"1912.02178","title":"Fantastic Generalization Measures and Where to Find Them","created":"2019-12-04","cited_by_count":513},{"id":"1705.08292","title":"The Marginal Value of Adaptive Gradient Methods in Machine Learning","created":"2017-05-23","cited_by_count":250},{"id":"1901.09401","title":"SGD: General Analysis and Improved Rates","created":"2019-01-27","cited_by_count":207},{"id":"1808.00387","title":"Just Interpolate: Kernel \"Ridgeless\" Regression Can Generalize","created":"2018-08-01","cited_by_count":190},{"id":"1806.01811","title":"AdaGrad stepsizes: Sharp convergence over nonconvex landscapes","created":"2018-06-05","cited_by_count":182},{"id":"2003.02395","title":"A Simple Convergence Proof of Adam and Adagrad","created":"2020-03-05","cited_by_count":171},{"id":"1712.06559","title":"The Power of Interpolation: Understanding the Effectiveness of SGD in Modern Over-parametrized Learning","created":"2017-12-18","cited_by_count":150},{"id":"1805.12076","title":"Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networks","created":"2018-05-30","cited_by_count":142},{"id":"2002.10542","title":"Stochastic Polyak Step-size for SGD: An Adaptive Learning Rate for Fast Convergence","created":"2020-02-24","cited_by_count":137},{"id":"2306.06101","title":"Prodigy: An Expeditiously Adaptive Parameter-Free Learner","created":"2023-06-09","cited_by_count":133},{"id":"2301.07733","title":"Learning-Rate-Free Learning by D-Adaptation","created":"2023-01-18","cited_by_count":113},{"id":"1910.09529","title":"Adaptive Gradient Descent without Descent","created":"2019-10-21","cited_by_count":79},{"id":"2010.04925","title":"Regularizing Neural Networks via Adversarial Model Perturbation","created":"2020-10-10","cited_by_count":78},{"id":"2006.10311","title":"SGD for Structured Nonconvex Functions: Learning Rates, Minibatching and Interpolation","created":"2020-06-18","cited_by_count":67},{"id":"1905.00313","title":"Revisiting the Polyak step size","created":"2019-05-01","cited_by_count":55},{"id":"1906.02613","title":"Bad Global Minima Exist and SGD Can Reach Them","created":"2019-06-06","cited_by_count":49},{"id":"2205.04583","title":"Dynamics of SGD with Stochastic Polyak Stepsizes: Truly Adaptive Variants and Convergence to Exact Solution","created":"2022-05-09","cited_by_count":40},{"id":"2305.16292","title":"Sharpness-Aware Minimization Leads to Low-Rank Features","created":"2023-05-25","cited_by_count":38},{"id":"1803.02461","title":"Subgradient methods for sharp weakly convex functions","created":"2018-03-06","cited_by_count":33},{"id":"2305.15287","title":"The Crucial Role of Normalization in Sharpness-Aware Minimization","created":"2023-05-24","cited_by_count":26},{"id":"2305.07583","title":"MoMo: Momentum Models for Adaptive Learning Rates","created":"2023-05-12","cited_by_count":24},{"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},{"id":"2306.09850","title":"Practical Sharpness-Aware Minimization Cannot Converge All the Way to Optima","created":"2023-06-16","cited_by_count":20},{"id":"2202.12328","title":"Cutting Some Slack for SGD with Adaptive Polyak Stepsizes","created":"2022-02-24","cited_by_count":18},{"id":"2102.09700","title":"AI-SARAH: Adaptive and Implicit Stochastic Recursive Gradient Methods","created":"2021-02-19","cited_by_count":15},{"id":"2301.04935","title":"A Stochastic Proximal Polyak Step Size","created":"2023-01-12","cited_by_count":15},{"id":"2305.12939","title":"Generalized Polyak Step Size for First Order Optimization with Momentum","created":"2023-05-22","cited_by_count":15},{"id":"2401.08060","title":"Fundamental Convergence Analysis of Sharpness-Aware Minimization","created":"2024-01-16","cited_by_count":14},{"id":"2406.03682","title":"A Universal Class of Sharpness-Aware Minimization Algorithms","created":"2024-06-06","cited_by_count":14},{"id":"2406.04142","title":"Stochastic Polyak Step-sizes and Momentum: Convergence Guarantees and Practical Performance","created":"2024-06-06","cited_by_count":13},{"id":"2407.04358","title":"An Adaptive Stochastic Gradient Method with Non-negative Gauss-Newton Stepsizes","created":"2024-07-05","cited_by_count":10},{"id":"2503.02225","title":"Sharpness-Aware Minimization: General Analysis and Improved Rates","created":"2025-03-04","cited_by_count":10},{"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},{"id":"2403.02648","title":"Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGrad","created":"2024-03-05","cited_by_count":8},{"id":"2502.02407","title":"Avoiding spurious sharpness minimization broadens applicability of SAM","created":"2025-02-04","cited_by_count":8},{"id":"2307.06306","title":"Locally Adaptive Federated Learning","created":"2023-07-12","cited_by_count":7},{"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},{"id":"2407.12993","title":"Improving SAM Requires Rethinking its Optimization Formulation","created":"2024-07-17","cited_by_count":4},{"id":"2311.17539","title":"Critical Influence of Overparameterization on Sharpness-aware Minimization","created":"2023-11-29","cited_by_count":3},{"id":"2505.24399","title":"LightSAM: Parameter-Agnostic Sharpness-Aware Minimization","created":"2025-05-30","cited_by_count":3},{"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}],"next_cursor":null}