{"list":"other","total":52,"rows":[{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1801.04406","title":"Which Training Methods for GANs do actually Converge?","created":"2018-01-13","cited_by_count":679},{"id":"1901.08584","title":"Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks","created":"2019-01-24","cited_by_count":566},{"id":"1905.11881","title":"Why gradient clipping accelerates training: A theoretical justification for adaptivity","created":"2019-05-28","cited_by_count":341},{"id":"1503.01243","title":"A Differential Equation for Modeling Nesterov's Accelerated Gradient Method: Theory and Insights","created":"2015-03-04","cited_by_count":206},{"id":"1806.05500","title":"Statistical Aspects of Wasserstein Distances","created":"2018-06-14","cited_by_count":203},{"id":"2010.05893","title":"Large-Scale Methods for Distributionally Robust Optimization","created":"2020-10-12","cited_by_count":179},{"id":"1802.10551","title":"A Variational Inequality Perspective on Generative Adversarial Networks","created":"2018-02-28","cited_by_count":144},{"id":"1901.08511","title":"A Unified Analysis of Extra-gradient and Optimistic Gradient Methods for Saddle Point Problems: Proximal Point Approach","created":"2019-01-24","cited_by_count":143},{"id":"2310.01082","title":"Linear attention is (maybe) all you need (to understand transformer optimization)","created":"2023-10-02","cited_by_count":98},{"id":"2011.00364","title":"Efficient Methods for Structured Nonconvex-Nonconcave Min-Max Optimization","created":"2020-10-31","cited_by_count":96},{"id":"1908.08465","title":"On the convergence of single-call stochastic extra-gradient methods","created":"2019-08-22","cited_by_count":89},{"id":"2010.00892","title":"Variance-Reduced Methods for Machine Learning","created":"2020-10-02","cited_by_count":79},{"id":"1911.00809","title":"Enhanced Convolutional Neural Tangent Kernels","created":"2019-11-03","cited_by_count":76},{"id":"2102.07922","title":"Accelerated Algorithms for Smooth Convex-Concave Minimax Problems with $\\mathcal{O}(1/k^2)$ Rate on Squared Gradient Norm","created":"2021-02-16","cited_by_count":73},{"id":"1810.08907","title":"Understanding the Acceleration Phenomenon via High-Resolution Differential Equations","created":"2018-10-21","cited_by_count":69},{"id":"2102.04540","title":"Last-iterate Convergence of Decentralized Optimistic Gradient Descent/Ascent in Infinite-horizon Competitive Markov Games","created":"2021-02-08","cited_by_count":69},{"id":"2106.02326","title":"Fast Extra Gradient Methods for Smooth Structured Nonconvex-Nonconcave Minimax Problems","created":"2021-06-04","cited_by_count":62},{"id":"2002.08872","title":"Halpern Iteration for Near-Optimal and Parameter-Free Monotone Inclusion and Strong Solutions to Variational Inequalities","created":"2020-02-20","cited_by_count":61},{"id":"2002.00057","title":"Last Iterate is Slower than Averaged Iterate in Smooth Convex-Concave Saddle Point Problems","created":"2020-01-31","cited_by_count":60},{"id":"2012.04061","title":"Faster Non-Convex Federated Learning via Global and Local Momentum","created":"2020-12-07","cited_by_count":48},{"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},{"id":"2202.07262","title":"Stochastic Gradient Descent-Ascent: Unified Theory and New Efficient Methods","created":"2022-02-15","cited_by_count":37},{"id":"2303.02854","title":"Generalized-Smooth Nonconvex Optimization is As Efficient As Smooth Nonconvex Optimization","created":"2023-03-06","cited_by_count":35},{"id":"2210.03096","title":"Accelerated Single-Call Methods for Constrained Min-Max Optimization","created":"2022-10-06","cited_by_count":32},{"id":"2111.08611","title":"Stochastic Extragradient: General Analysis and Improved Rates","created":"2021-11-16","cited_by_count":31},{"id":"2010.12100","title":"Adaptive extra-gradient methods for min-max optimization and games","created":"2020-10-22","cited_by_count":30},{"id":"1902.09827","title":"Generalized monotone operators and their averaged resolvents","created":"2019-02-26","cited_by_count":27},{"id":"2106.08315","title":"Decentralized Local Stochastic Extra-Gradient for Variational Inequalities","created":"2021-06-15","cited_by_count":25},{"id":"2201.11413","title":"Exact Optimal Accelerated Complexity for Fixed-Point Iterations","created":"2022-01-27","cited_by_count":25},{"id":"2409.14989","title":"Methods for Convex $(L_0,L_1)$-Smooth Optimization: Clipping, Acceleration, and Adaptivity","created":"2024-09-23","cited_by_count":25},{"id":"2208.13614","title":"Neural Tangent Kernel: A Survey","created":"2022-08-29","cited_by_count":23},{"id":"2110.08150","title":"Halpern-Type Accelerated and Splitting Algorithms For Monotone Inclusions","created":"2021-10-15","cited_by_count":21},{"id":"2302.09029","title":"Solving stochastic weak Minty variational inequalities without increasing batch size","created":"2023-02-17","cited_by_count":21},{"id":"2302.09831","title":"Escaping limit cycles: Global convergence for constrained nonconvex-nonconcave minimax problems","created":"2023-02-20","cited_by_count":21},{"id":"2203.04869","title":"From Halpern's Fixed-Point Iterations to Nesterov's Accelerated Interpretations for Root-Finding Problems","created":"2022-03-09","cited_by_count":20},{"id":"2106.05958","title":"High Probability Complexity Bounds for Non-Smooth Stochastic Optimization with Heavy-Tailed Noise","created":"2021-06-10","cited_by_count":19},{"id":"2410.10800","title":"Optimizing $(L_0, L_1)$-Smooth Functions by Gradient Methods","created":"2024-10-14","cited_by_count":19},{"id":"2203.07305","title":"Branch-and-Bound Performance Estimation Programming: A Unified Methodology for Constructing Optimal Optimization Methods","created":"2022-03-14","cited_by_count":16},{"id":"1812.00146","title":"Operator Splitting Performance Estimation: Tight contraction factors and optimal parameter selection","created":"2018-12-01","cited_by_count":13},{"id":"2101.09583","title":"Communication-Efficient Variance-Reduced Decentralized Stochastic Optimization over Time-Varying Directed Graphs","created":"2021-01-23","cited_by_count":9},{"id":"2303.17192","title":"Sublinear Convergence Rates of Extragradient-Type Methods: A Survey on Classical and Recent Developments","created":"2023-03-30","cited_by_count":5},{"id":"2407.16144","title":"Restarted Halpern PDHG for Linear Programming","created":"2024-07-23","cited_by_count":5},{"id":"1810.02555","title":"Differentiable Antithetic Sampling for Variance Reduction in Stochastic Variational Inference","created":"2018-10-05","cited_by_count":4},{"id":"2308.12359","title":"Moving Anchor Extragradient Methods For Smooth Structured Minimax Problems","created":"2023-08-23","cited_by_count":3},{"id":"2510.22421","title":"Extragradient Method for $(L_0, L_1)$-Lipschitz Root-finding Problems","created":"2025-10-25","cited_by_count":3},{"id":"2409.16859","title":"Revisiting Extragradient-Type Methods -- Part 1: Generalizations and Sublinear Convergence Rates","created":"2024-09-25","cited_by_count":2},{"id":"2501.04585","title":"Accelerated Extragradient-Type Methods -- Part 2: Generalization and Sublinear Convergence Rates under Co-Hypomonotonicity","created":"2025-01-08","cited_by_count":2},{"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},{"id":"2402.05691","title":"Adaptive Methods for Variational Inequalities under Relaxed Smoothness Assumption","created":"2024-02-08","cited_by_count":1},{"id":"2406.10793","title":"Symplectic Extra-gradient Type Method for Solving General Non-monotone Inclusion Problem","created":"2024-06-16","cited_by_count":1}],"next_cursor":null}