资源分类
》 资源 》论文》Maximum Selection and Ranking under Noisy Comparisons

Maximum Selection and Ranking under Noisy Comparisons

2020-03-09 | |  58 |   50 |   0

Abstract

We consider (ε,δ)-PAC maximum-selection and ranking using pairwise comparisons for general probabilistic models whose comparison probabilities satisfy strong stochastic transitivity an stochastic triangle inequality. Modifying the popular knockout tournament, we propose a simple maximum-selection algorithm that uses 图片.png comparisons, optimal up to a constant factor. We then derive a general framework that uses noisy binary search to speed up many ranking algorithms, and combine it with merge sort to obtain a ranking algorithm that uses 图片.png comparisons for 图片.png optimal up to 图片.png factor.

上一篇：Conditional Image Synthesis with Auxiliary Classifier GANs

下一篇：Max-value Entropy Search for Efficient Bayesian Optimization

用户评价
全部评价

热门资源

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...