预算约束在线学习的最优节奏与遗憾界研究

1. 12:00
   arXiv · Machine Learning Theory

   预算支出与学习的最佳节奏控制

   该研究在对抗设定下，针对任意预算节奏专家类给出了接近最优的遗憾界。对于 F 个专家和给定的候选预算节奏方案，所提全信息算法对累计支出与方案距离在 D 内的专家取得 O(D√log F + √(T log F)) 遗憾，匹配 Braverman et al. (2025) 的下界。

Current heat 9·Comparable peak 10（Oct 9）·Comparable change over 24 hours –

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.