异质偏好下排名恢复所需重复成对比较次数研究

1. 12:00
   arXiv · Machine Learning Theory

   异质偏好下排序恢复需要多少次重复两两比较

   该研究在异质 Bradley-Terry 模型下分析按总体平均效用做排序所需的重复两两比较次数，证明朴素 MLE 算法需 Ω(1/Δ²) 次、两种 MLE 变体与 Russian Roulette 随机算法仅需 O(log(1/Δ)) 次且该对数依赖最优。

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.