Rejection sampling from shape-constrained distributions in sublinear time

05/29/2021
by   Sinho Chewi, et al.
0

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 𝒪(K) to 𝒪(log^2 K), where K is the number of arms.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

05/31/2019

Exact sampling of determinantal point processes with sublinear time preprocessing

We study the complexity of sampling from a distribution over all index s...
05/29/2021

The query complexity of sampling from strongly log-concave distributions in one dimension

We establish the first tight lower bound of Ω(loglogκ) on the query comp...
02/26/2020

Memory-Constrained No-Regret Learning in Adversarial Bandits

An adversarial bandit problem with memory constraints is studied where o...
02/10/2021

On the Suboptimality of Thompson Sampling in High Dimensions

In this paper we consider Thompson Sampling for combinatorial semi-bandi...
06/01/2017

Scalable Generalized Linear Bandits: Online Computation and Hashing

Generalized Linear Bandits (GLBs), a natural extension of the stochastic...
09/14/2021

Domain Sparsification of Discrete Distributions using Entropic Independence

We present a framework for speeding up the time it takes to sample from ...
12/12/2017

Dynamic Discrete Tomography

We consider the problem of reconstructing the paths of a set of points o...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.