{"total":63,"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":"2102.06555","title":"Online Graph Dictionary Learning","created":"2021-02-12","cited_by_count":37,"area":null},{"id":"2501.00365","title":"Low-Rank Adaptation for Foundation Models: A Comprehensive Review","created":"2024-12-31","cited_by_count":37,"area":null},{"id":"2110.02753","title":"Semi-relaxed Gromov-Wasserstein divergence with applications on graphs","created":"2021-10-06","cited_by_count":21,"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":"2205.15733","title":"Template based Graph Neural Network with Optimal Transport Distances","created":"2022-05-31","cited_by_count":20,"area":null},{"id":"2405.17897","title":"$C^2M^3$: Cycle-Consistent Multi-Model Merging","created":"2024-05-28","cited_by_count":20,"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":"2206.08868","title":"A Conditional Gradient-based Method for Simple Bilevel Optimization with Convex Lower-level Problem","created":"2022-06-17","cited_by_count":17,"area":null},{"id":"2312.12065","title":"PPO-Clip Attains Global Optimality: Towards Deeper Understandings of Clipping","created":"2023-12-19","cited_by_count":17,"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":"2308.07536","title":"Projection-Free Methods for Stochastic Simple Bilevel Optimization with Convex Lower-level Problem","created":"2023-08-15","cited_by_count":13,"area":null},{"id":"2402.02239","title":"Distributional Reduction: Unifying Dimensionality Reduction and Clustering with Gromov-Wasserstein","created":"2024-02-03","cited_by_count":12,"area":null},{"id":"2603.05002","title":"Non-Euclidean Gradient Descent Operates at the Edge of Stability","created":"2026-03-05","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":"2211.03352","title":"Curriculum-based Asymmetric Multi-task Reinforcement Learning","created":"2022-11-07","cited_by_count":8,"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":"2401.08330","title":"Boosting Gradient Ascent for Continuous DR-submodular Maximization","created":"2024-01-16","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":"2312.16335","title":"LeanVec: Searching vectors faster by making them fit","created":"2023-12-26","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":"2503.12649","title":"FW-Merging: Scaling Model Merging with Frank-Wolfe Optimization","created":"2025-03-16","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":"2110.10932","title":"Subspace Detours Meet Gromov-Wasserstein","created":"2021-10-21","cited_by_count":4,"area":null},{"id":"2405.15505","title":"Revisiting Counterfactual Regression through the Lens of Gromov-Wasserstein Information Bottleneck","created":"2024-05-24","cited_by_count":4,"area":null},{"id":"2206.09370","title":"Frank-Wolfe-based Algorithms for Approximating Tyler's M-estimator","created":"2022-06-19","cited_by_count":3,"area":null},{"id":"2305.11046","title":"Difference of Submodular Minimization via DC Programming","created":"2023-05-18","cited_by_count":3,"area":null},{"id":"2404.01200","title":"Large-Scale Non-convex Stochastic Constrained Distributionally Robust Optimization","created":"2024-04-01","cited_by_count":3,"area":null},{"id":"2210.11413","title":"Minimizing low-rank models of high-order tensors: Hardness, span, tight relaxation, and applications","created":"2022-10-16","cited_by_count":2,"area":null},{"id":"2212.07495","title":"SAIF: Sparse Adversarial and Imperceptible Attack Framework","created":"2022-12-14","cited_by_count":2,"area":null},{"id":"2302.12808","title":"Linearization Algorithms for Fully Composite Optimization","created":"2023-02-24","cited_by_count":2,"area":null},{"id":"2306.01787","title":"Power Control with QoS Guarantees: A Differentiable Projection-based Unsupervised Learning Framework","created":"2023-05-31","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":"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":"2604.02554","title":"Principled and Scalable Diversity-Aware Retrieval via Cardinality-Constrained Binary Quadratic Programming","created":"2026-04-02","cited_by_count":2,"area":"rag"},{"id":"2605.30337","title":"Efficient Test-Time Finetuning of LLMs via Convex Reconstruction and Gradient Caching","created":"2026-05-28","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":"2110.02554","title":"A Regularized Wasserstein Framework for Graph Kernels","created":"2021-10-06","cited_by_count":1,"area":null},{"id":"2205.08115","title":"Fast and Provably Convergent Algorithms for Gromov-Wasserstein in Graph Data","created":"2022-05-17","cited_by_count":1,"area":null},{"id":"2311.13883","title":"Leveraging Optimal Transport via Projections on Subspaces for Machine Learning Applications","created":"2023-11-23","cited_by_count":1,"area":null},{"id":"2501.18143","title":"Double-Bounded Nonlinear Optimal Transport for Size Constrained Min Cut Clusterin","created":"2025-01-30","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":"2504.20908","title":"MOSIC: Model-Agnostic Optimal Subgroup Identification with Multi-Constraint for Improved Reliability","created":"2025-04-29","cited_by_count":1,"area":null},{"id":"2507.17545","title":"Scalable DC Optimization via Adaptive Frank-Wolfe Algorithms","created":"2025-07-23","cited_by_count":1,"area":null},{"id":"2602.11387","title":"Provably Efficient Algorithms for S- and Non-Rectangular Robust MDPs with General Parameterization","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2608.27774","title":"Beyond Procrustes distances: a multilinear Gromov-Wasserstein distance capturing chirality","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2105.03527","title":"Scalable Projection-Free Optimization","created":"2021-05-07","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":"2310.12081","title":"Robust Graph Matching Using An Unbalanced Hierarchical Optimal Transport Framework","created":"2023-10-18","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":"2501.07201","title":"An Enhanced Zeroth-Order Stochastic Frank-Wolfe Framework for Constrained Finite-Sum Optimization","created":"2025-01-13","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":"2605.01580","title":"Model Merging: Foundations and Algorithms","created":"2026-05-02","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":"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":"2605.12161","title":"Fused Gromov-Wasserstein Distance with Feature Selection","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.30807","title":"Conformal Reliability: A New Evaluation Metric for Conditional Generation","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.02223","title":"Network Learning with Semi-relaxed Gromov-Wasserstein","created":"2026-06-01","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}