高维在线校准的调和权重算法

1. 12:00
   arXiv · Statistics Machine Learning

   基于调和权重的高维在线校准

   研究给出针对任意凸集与误差范数的高维预测在线校准算法。对 d 个二元结果同时预测，该算法在固定精度下以 d^{O(1/ε)} 轮达到 ε-校准，指数级改进此前界；对多类预测同样达到 d^{O(1/ε)}，优于 Peng 与 Fishelson 等人的 d^{\widetilde{O}(1/ε^2)}。

Current heat 9·Comparable peak 10（Oct 7）·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.