{"total":41,"rows":[{"id":"2401.04151","title":"Chain of LoRA: Efficient Fine-tuning of Language Models via Residual Learning","created":"2024-01-08","cited_by_count":82,"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":"2309.15639","title":"Enhancing Sharpness-Aware Optimization Through Variance Suppression","created":"2023-09-27","cited_by_count":37,"area":null},{"id":"2305.05080","title":"Scalable Optimal Transport Methods in Machine Learning: A Contemporary Survey","created":"2023-05-08","cited_by_count":27,"area":null},{"id":"2106.13015","title":"A Stochastic Sequential Quadratic Optimization Algorithm for Nonlinear Equality Constrained Optimization with Rank-Deficient Jacobians","created":"2021-06-24","cited_by_count":22,"area":null},{"id":"2101.10040","title":"Complexity of Linear Minimization and Projection on Some Sets","created":"2021-01-25","cited_by_count":20,"area":null},{"id":"2111.15139","title":"Breaking the Linear Iteration Cost Barrier for Some Well-known Conditional Gradient Methods Using MaxIP Data-structures","created":"2021-11-30","cited_by_count":19,"area":null},{"id":"2102.11055","title":"Escaping from Zero Gradient: Revisiting Action-Constrained Reinforcement Learning via Frank-Wolfe Policy Optimization","created":"2021-02-22","cited_by_count":18,"area":null},{"id":"2205.11921","title":"Compression-aware Training of Neural Networks using Frank-Wolfe","created":"2022-05-24","cited_by_count":16,"area":null},{"id":"2205.13573","title":"Efficient Approximation of Gromov-Wasserstein Distance Using Importance Sparsification","created":"2022-05-26","cited_by_count":11,"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":"2207.14200","title":"CrAM: A Compression-Aware Minimizer","created":"2022-07-28","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":"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":"2106.06741","title":"Distributionally Robust Optimization with Markovian Data","created":"2021-06-12","cited_by_count":4,"area":null},{"id":"2110.13103","title":"Shift of Pairwise Similarities for Data Clustering","created":"2021-10-25","cited_by_count":4,"area":null},{"id":"2310.06069","title":"Optimal Exploration is no harder than Thompson Sampling","created":"2023-10-09","cited_by_count":3,"area":null},{"id":"2212.06283","title":"Variance-Reduced Conservative Policy Iteration","created":"2022-12-12","cited_by_count":2,"area":null},{"id":"2401.05667","title":"EsaCL: Efficient Continual Learning of Sparse Models","created":"2024-01-11","cited_by_count":2,"area":null},{"id":"2406.03787","title":"Projection-Free Variance Reduction Methods for Stochastic Constrained Multi-Level Compositional Optimization","created":"2024-06-06","cited_by_count":2,"area":null},{"id":"2406.14743","title":"A General Online Algorithm for Optimizing Complex Performance Metrics","created":"2024-06-20","cited_by_count":2,"area":null},{"id":"2510.13713","title":"Don't Be Greedy, Just Relax! Pruning LLMs via Frank-Wolfe","created":"2025-10-15","cited_by_count":2,"area":null},{"id":"2606.18650","title":"BLADE: Scalable Bi-level Adaptive Data Selection for LLM Training","created":"2026-06-17","cited_by_count":2,"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":"2502.02197","title":"An Efficient Local Search Approach for Polarized Community Discovery in Signed Networks","created":"2025-02-04","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":"2512.12550","title":"Iterative Sampling Methods for Sinkhorn Distributionally Robust Optimization","created":"2025-12-14","cited_by_count":1,"area":null},{"id":"2603.06369","title":"Adaptive Lipschitz-Free Conditional Gradient Methods for Stochastic Composite Nonconvex Optimization","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2606.14929","title":"Policy Regret for Embedding Model Routing: Contextual Bandits with Low-Rank Experts","created":"2026-06-12","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":"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":"2408.10090","title":"Federated Frank-Wolfe Algorithm","created":"2024-08-19","cited_by_count":0,"area":null},{"id":"2510.02735","title":"Quantitative Convergence Analysis of Projected Stochastic Gradient Descent for Non-Convex Losses via the Goldstein Subdifferential","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2604.14587","title":"CLion: Efficient Cautious Lion Optimizer with Enhanced Generalization","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2605.05577","title":"Accelerating LMO-Based Optimization via Implicit Gradient Transport","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2607.25190","title":"Lloyd's $K$-Means Clustering Algorithm Is Frank-Wolfe in Disguise","created":"2026-07-28","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},{"id":"2610.13787","title":"Optimal Algorithms for Nonsmooth Nonconvex Stochastic Optimization with Constraints","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}