The Sample Complexity of Approximate Rejection Sampling with Applications to Smoothed Online Learning
arxiv(2023)
摘要
Suppose we are given access to n independent samples from distribution
μ and we wish to output one of them with the goal of making the output
distributed as close as possible to a target distribution ν. In this work
we show that the optimal total variation distance as a function of n is given
by Θ̃(D/f'(n)) over the class of all pairs ν,μ with a
bounded f-divergence D_f(νμ)≤ D. Previously, this question was
studied only for the case when the Radon-Nikodym derivative of ν with
respect to μ is uniformly bounded. We then consider an application in the
seemingly very different field of smoothed online learning, where we show that
recent results on the minimax regret and the regret of oracle-efficient
algorithms still hold even under relaxed constraints on the adversary (to have
bounded f-divergence, as opposed to bounded Radon-Nikodym derivative).
Finally, we also study efficacy of importance sampling for mean estimates
uniform over a function class and compare importance sampling with rejection
sampling.
更多查看译文
关键词
approximate rejection sampling,sample complexity
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要