{"total":22,"rows":[{"id":"2502.07529","title":"Training Deep Learning Models with Norm-Constrained LMOs","created":"2025-02-11","cited_by_count":192,"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":"2305.00241","title":"When Deep Learning Meets Polyhedral Theory: A Survey","created":"2023-04-29","cited_by_count":39,"area":null},{"id":"2102.11646","title":"HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search","created":"2021-02-23","cited_by_count":20,"area":null},{"id":"2306.16788","title":"Sparse Model Soups: A Recipe for Improved Pruning via Model Averaging","created":"2023-06-29","cited_by_count":20,"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":"2206.00759","title":"Interpretability Guarantees with Merlin-Arthur Classifiers","created":"2022-06-01","cited_by_count":9,"area":null},{"id":"2207.01236","title":"Approximate Vanishing Ideal Computations at Scale","created":"2022-07-04","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":"2403.12511","title":"Projected Forward Gradient-Guided Frank-Wolfe Algorithm via Variance Reduction","created":"2024-03-19","cited_by_count":5,"area":null},{"id":"2502.15051","title":"Approximating Latent Manifolds in Neural Networks via Vanishing Ideals","created":"2025-02-20","cited_by_count":5,"area":null},{"id":"2108.00259","title":"How much pre-training is enough to discover a good subnetwork?","created":"2021-07-31","cited_by_count":4,"area":null},{"id":"2202.11797","title":"Training Characteristic Functions with Reinforcement Learning: XAI-methods play Connect Four","created":"2022-02-23","cited_by_count":3,"area":null},{"id":"2401.05667","title":"EsaCL: Efficient Continual Learning of Sparse Models","created":"2024-01-11","cited_by_count":2,"area":null},{"id":"2404.09438","title":"Developing Lagrangian-based Methods for Nonsmooth Nonconvex Optimization","created":"2024-04-15","cited_by_count":2,"area":null},{"id":"2503.08921","title":"Revisiting Frank-Wolfe for Structured Nonconvex Optimization","created":"2025-03-11","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":"2112.04905","title":"i-SpaSP: Structured Neural Pruning via Sparse Signal Recovery","created":"2021-12-07","cited_by_count":1,"area":null},{"id":"2501.16322","title":"Implicit Bias in Matrix Factorization and its Explicit Realization in a New Architecture","created":"2025-01-27","cited_by_count":1,"area":null},{"id":"2512.01147","title":"Projection-Free CNN Pruning via Frank-Wolfe with Momentum: Sparser Models with Less Pretraining","created":"2025-11-30","cited_by_count":0,"area":null},{"id":"2605.08850","title":"Broximal Gradient Descent: A Projection-Free Sister of Projected Gradient Descent","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2609.33383","title":"Local LMO is Secretly a Projection Method!","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}