Learning Sums of Independent Random Variables with Sparse Collective Support

TL;DR

This paper develops efficient algorithms for learning sums of independent integer random variables with limited collective support, providing optimal sample complexity bounds for small support sets and extending results to unknown supports.

Contribution

It introduces new algorithms with optimal sample complexity for learning sums of independent integer variables with small support sets, including unknown support cases.

Findings

For support size 3, polynomial-time learning algorithm with sample complexity independent of N.

For support size k ≥ 4, algorithms with sample complexity depending on log log of maximum support element.

Lower bounds showing the necessity of log log support size in sample complexity.

Abstract

We study the learnability of sums of independent integer random variables given a bound on the size of the union of their supports. For $\mathcal{A} \subset \mathbf{Z}_{+}$, a sum of independent random variables with collective support $\mathcal{A}$} (called an $\mathcal{A}$-sum in this paper) is a distribution $\mathbf{S} = \mathbf{X}_1 + \cdots + \mathbf{X}_N$ where the $\mathbf{X}_i$'s are mutually independent (but not necessarily identically distributed) integer random variables with $\cup_i \mathsf{supp}(\mathbf{X}_i) \subseteq \mathcal{A}.$ We give two main algorithmic results for learning such distributions: 1. For the case $| \mathcal{A} | = 3$, we give an algorithm for learning $\mathcal{A}$-sums to accuracy $\epsilon$ that uses $\mathsf{poly}(1/\epsilon)$ samples and runs in time $\mathsf{poly}(1/\epsilon)$, independent of $N$ and of the elements of $\mathcal{A}$. 2. For an arbitrary constant $k \geq 4$, if $\mathcal{A} = \{ a_1,...,a_k\}$ with $0 \leq a_1 < ... < a_k$, we give an algorithm that uses $\mathsf{poly}(1/\epsilon) \cdot \log \log a_k$ samples (independent of $N$) and runs in time $\mathsf{poly}(1/\epsilon, \log a_k).$ We prove an essentially matching lower bound: if $|\mathcal{A}| = 4$, then any algorithm must use $\Omega(\log \log a_4) $ samples even for learning to constant accuracy. We also give similar-in-spirit (but quantitatively very different) algorithmic results, and essentially matching lower bounds, for the case in which $\mathcal{A}$ is not known to the learner.