{"total":47,"rows":[{"id":"2502.07529","title":"Training Deep Learning Models with Norm-Constrained LMOs","created":"2025-02-11","cited_by_count":192,"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":"2506.04192","title":"Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise","created":"2025-06-04","cited_by_count":41,"area":null},{"id":"2102.11050","title":"Online Learning via Offline Greedy Algorithms: Applications in Market Design and Optimization","created":"2021-02-18","cited_by_count":40,"area":null},{"id":"2202.00132","title":"Submodularity In Machine Learning and Artificial Intelligence","created":"2022-01-31","cited_by_count":38,"area":null},{"id":"2309.15639","title":"Enhancing Sharpness-Aware Optimization Through Variance Suppression","created":"2023-09-27","cited_by_count":37,"area":null},{"id":"2509.15816","title":"On the Convergence of Muon and Beyond","created":"2025-09-19","cited_by_count":31,"area":null},{"id":"2507.01598","title":"Convergence Bound and Critical Batch Size of Muon Optimizer","created":"2025-07-02","cited_by_count":28,"area":null},{"id":"2105.14024","title":"Near-Optimal Multi-Perturbation Experimental Design for Causal Structure Learning","created":"2021-05-28","cited_by_count":17,"area":null},{"id":"2506.01913","title":"Generalized Gradient Norm Clipping & Non-Euclidean $(L_0,L_1)$-Smoothness","created":"2025-06-02","cited_by_count":17,"area":null},{"id":"2311.00678","title":"Complexity of Single Loop Algorithms for Nonlinear Programming with Stochastic Objective and Constraints","created":"2023-11-01","cited_by_count":16,"area":null},{"id":"2108.09767","title":"A Boosting Approach to Reinforcement Learning","created":"2021-08-22","cited_by_count":12,"area":null},{"id":"2305.16671","title":"A Unified Approach for Maximizing Continuous DR-submodular Functions","created":"2023-05-26","cited_by_count":10,"area":null},{"id":"2603.14315","title":"Enhancing LLM Training via Spectral Clipping","created":"2026-03-15","cited_by_count":10,"area":null},{"id":"2405.00065","title":"From Linear to Linearizable Optimization: A Novel Framework with Applications to Stationary and Non-stationary DR-submodular Optimization","created":"2024-04-27","cited_by_count":9,"area":null},{"id":"2110.11721","title":"Projection-Free Algorithm for Stochastic Bi-level Optimization","created":"2021-10-22","cited_by_count":8,"area":null},{"id":"2202.04296","title":"A Projection-free Algorithm for Constrained Stochastic Multi-level Composition Optimization","created":"2022-02-09","cited_by_count":8,"area":null},{"id":"2110.04243","title":"Heavy Ball Momentum for Conditional Gradient","created":"2021-10-08","cited_by_count":7,"area":null},{"id":"2304.11737","title":"Sarah Frank-Wolfe: Methods for Constrained Optimization with Best Rates and Practical Features","created":"2023-04-23","cited_by_count":7,"area":null},{"id":"2107.06534","title":"Zeroth and First Order Stochastic Frank-Wolfe Algorithms for Constrained Optimization","created":"2021-07-14","cited_by_count":6,"area":null},{"id":"2206.11346","title":"Constrained Stochastic Nonconvex Optimization with State-dependent Markov Data","created":"2022-06-22","cited_by_count":6,"area":null},{"id":"2208.08681","title":"Communication-Efficient Decentralized Online Continuous DR-Submodular Maximization","created":"2022-08-18","cited_by_count":6,"area":null},{"id":"2605.09238","title":"Intrinsic Muon: Spectral Optimization on Riemannian Matrix Manifolds","created":"2026-05-10","cited_by_count":6,"area":null},{"id":"2110.08105","title":"Interpretable Neural Networks with Frank-Wolfe: Sparse Relevance Maps and Relevance Orderings","created":"2021-10-15","cited_by_count":5,"area":null},{"id":"2111.01262","title":"Minimax Optimization: The Case of Convex-Submodular","created":"2021-11-01","cited_by_count":5,"area":null},{"id":"2403.10063","title":"Unified Projection-Free Algorithms for Adversarial DR-Submodular Optimization","created":"2024-03-15","cited_by_count":5,"area":null},{"id":"2402.08621","title":"A Unified Framework for Analyzing Meta-algorithms in Online Convex Optimization","created":"2024-02-13","cited_by_count":4,"area":null},{"id":"2208.07632","title":"Online Learning for Non-monotone Submodular Maximization: From Full Information to Bandit Feedback","created":"2022-08-16","cited_by_count":3,"area":null},{"id":"2605.11172","title":"Optimistic Dual Averaging Unifies Modern Optimizers","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2606.14560","title":"Free Heavy-Tailed Lunch for Muon: A Theoretical Justification of Empirical Success","created":"2026-06-12","cited_by_count":2,"area":null},{"id":"2606.15268","title":"When to use what Schatten-$p$ norm in deep learning?","created":"2026-06-13","cited_by_count":2,"area":null},{"id":"2101.07423","title":"Submodular Maximization via Taylor Series Approximation","created":"2021-01-19","cited_by_count":1,"area":null},{"id":"2202.13212","title":"Faster One-Sample Stochastic Conditional Gradient Method for Composite Convex Minimization","created":"2022-02-26","cited_by_count":1,"area":null},{"id":"2509.02433","title":"VASSO: Variance Suppression for Sharpness-Aware Minimization","created":"2025-09-02","cited_by_count":1,"area":null},{"id":"2602.13506","title":"$\\gamma$-weakly $\\theta$-up-concavity: A Unified Framework for Non-Convex Optimization Beyond DR-Submodular and OSS Functions","created":"2026-02-13","cited_by_count":1,"area":null},{"id":"2605.15350","title":"Stochastic Compositional Optimization via Hybrid Momentum Frank--Wolfe","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2103.01484","title":"Online Orthogonal Dictionary Learning Based on Frank-Wolfe Method","created":"2021-03-02","cited_by_count":0,"area":null},{"id":"2105.03527","title":"Scalable Projection-Free Optimization","created":"2021-05-07","cited_by_count":0,"area":null},{"id":"2107.00472","title":"Approximate Frank-Wolfe Algorithms over Graph-structured Support Sets","created":"2021-06-29","cited_by_count":0,"area":null},{"id":"2208.13933","title":"Using Taylor-Approximated Gradients to Improve the Frank-Wolfe Method for Empirical Risk Minimization","created":"2022-08-30","cited_by_count":0,"area":null},{"id":"2303.09960","title":"Stochastic Submodular Maximization via Polynomial Estimators","created":"2023-03-17","cited_by_count":0,"area":null},{"id":"2303.11937","title":"High Probability Bounds for Stochastic Continuous Submodular Maximization","created":"2023-03-20","cited_by_count":0,"area":null},{"id":"2408.10090","title":"Federated Frank-Wolfe Algorithm","created":"2024-08-19","cited_by_count":0,"area":null},{"id":"2409.12053","title":"Extended Deep Submodular Functions","created":"2024-09-18","cited_by_count":0,"area":null},{"id":"2602.23277","title":"Zeroth-Order Stackelberg Control in Combinatorial Congestion Games","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2607.00680","title":"Distributed Online Bandit Submodular Maximization with Bounded Sampling Violations","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.25785","title":"Variance-Reduced Conditional Gradient Methods under Markovian Sampling for Nonconvex Composite Optimization","created":"2026-07-28","cited_by_count":0,"area":null}],"next_cursor":null}