{"total":14,"rows":[{"id":"2305.17333","title":"Fine-Tuning Language Models with Just Forward Passes","created":"2023-05-27","cited_by_count":345,"area":null},{"id":"2402.15173","title":"Second-Order Fine-Tuning without Pain for LLMs:A Hessian Informed Zeroth-Order Optimizer","created":"2024-02-23","cited_by_count":53,"area":null},{"id":"2506.09034","title":"FZOO: Fast Zeroth-Order Optimizer for Fine-Tuning Large Language Models towards Adam-Scale Speed","created":"2025-06-10","cited_by_count":14,"area":null},{"id":"2202.13046","title":"Distributed Multi-Agent Reinforcement Learning Based on Graph-Induced Local Value Functions","created":"2022-02-26","cited_by_count":6,"area":null},{"id":"2503.07324","title":"Decision-Dependent Stochastic Optimization: The Role of Distribution Dynamics","created":"2025-03-10","cited_by_count":6,"area":null},{"id":"2107.12416","title":"Asynchronous Distributed Reinforcement Learning for LQR Control via Zeroth-Order Block Coordinate Descent","created":"2021-07-26","cited_by_count":4,"area":null},{"id":"2303.13657","title":"Policy Evaluation in Distributional LQR","created":"2023-03-23","cited_by_count":1,"area":null},{"id":"2205.06968","title":"No-regret learning for repeated non-cooperative games with lossy bandits","created":"2022-05-14","cited_by_count":0,"area":null},{"id":"2409.15680","title":"Distributed Online Bandit Nonconvex Optimization with One-Point Residual Feedback via Dynamic Regret","created":"2024-09-24","cited_by_count":0,"area":null},{"id":"2409.16866","title":"Risk-averse learning with delayed feedback","created":"2024-09-25","cited_by_count":0,"area":null},{"id":"2510.25074","title":"BOND: License to Train with Black-Box Functions","created":"2025-10-29","cited_by_count":0,"area":null},{"id":"2512.22467","title":"GLUE: Gradient-free Learning to Unify Experts","created":"2025-12-27","cited_by_count":0,"area":null},{"id":"2601.20422","title":"Guiding the Recommender: Information-Aware Auto-Bidding for Content Promotion","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2607.23925","title":"Greedy dynamical meta-learning","created":"2026-07-27","cited_by_count":0,"area":null}],"next_cursor":null}