On Approximating Total Variation Distance

Abstract

Total variation distance (TV distance) is a fundamental notion of distance between probability distributions. In this work, we introduce and study the problem of computing the TV distance of two product distributions over the domain $\{0,1{\}}^n$. In particular, we establish the following results. 1. The problem of exactly computing the TV distance of two product distributions is $\#\mathsf{P}$-complete. This is in stark contrast with other distance measures such as KL, Chi-square, and Hellinger which tensorize over the marginals leading to efficient algorithms. 2. There is a fully polynomial-time deterministic approximation scheme (FPTAS) for computing the TV distance of two product distributions $P$ and $Q$ where $Q$ is the uniform distribution. This result is extended to the case where $Q$ has a constant number of distinct marginals. In contrast, we show that when $P$ and $Q$ are Bayes net distributions, the relative approximation of their TV distance is $\mathsf{NP}$-hard.

20 pages, 1 figure

References in corpus (1)

• Polynomial-Time Approximation Schemes for Knapsack and Related Counting Problems using Branching Programs

Cited by in corpus (2)

• Permutation-Based Distances for Groups and Group-Valued Time Series
• Bias Detection via Maximum Subgroup Discrepancy