arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2105.14166cs.LGmath.STstat.MLstat.TH
收藏

次线性时间下形状约束分布的拒绝抽样

Rejection sampling from shape-constrained distributions in sublinear time

MIT(麻省理工学院)

Sinho Chewi, Patrik Gerber, Chen Lu, Thibaut Le Gouic, Philippe Rigollet

摘要:

我们考虑的任务,从一个目标分布,已知的归一化,在一个有限的字母表生成精确的样本。该任务的经典算法是拒绝采样,尽管它已在实践中使用了几十年,但令人惊讶的是,对其基本局限性的研究却很少。在这项工作中,我们研究了查询的复杂性拒绝抽样在一个极大极小的框架,各类离散分布。我们的研究结果提供了新的算法采样的复杂度与字母表的大小呈次线性关系。当应用于对抗土匪,我们表明,略有修改的Exp3算法减少了每次迭代的复杂度从$\mathcal O(K)$到$\mathcal O(\log^2 K)$,其中$K$是武器的数量。

英文摘要:

We consider the task of generating exact samples from a target distribution, known up to normalization, over a finite alphabet. The classical algorithm for this task is rejection sampling, and although it has been used in practice for decades, there is surprisingly little study of its fundamental limitations. In this work, we study the query complexity of rejection sampling in a minimax framework for various classes of discrete distributions. Our results provide new algorithms for sampling whose complexity scales sublinearly with the alphabet size. When applied to adversarial bandits, we show that a slight modification of the Exp3 algorithm reduces the per-iteration complexity from $\mathcal O(K)$ to $\mathcal O(\log^2 K)$, where $K$ is the number of arms.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑