Learning Poisson Binomial Distributions
Preprint
Abstract
We consider a basic problem in unsupervised learning: learning an unknown \emph{Poisson Binomial Distribution}. A Poisson Binomial Distribution (PBD) over $\{0,1,\dots,n\}$ is the distribution of a sum of $n$ independent Bernoulli random variables which may have arbitrary, potentially non-equal, expectations. These distributions were first studied by S. Poisson in 1837 \cite{Poisson:37} and are a natural $n$-parameter generalization of the familiar Binomial Distribution. Surprisingly, prior to our work this basic learning problem was poorly understood, and known results for it were far from optimal. We essentially settle the complexity of the learning problem for this basic class of distributions. As our first main result we give a highly efficient algorithm which learns to $\eps$-accuracy (with respect to the total variation distance) using $\tilde{O}(1/\eps^3)$ samples \emph{independent of $n$}. The running time of the algorithm is \emph{quasilinear} in the size of its input data, i.e., $\tilde{O}(\log(n)/\eps^3)$ bit-operations. (Observe that each draw from the distribution is a $\log(n)$-bit string.) Our second main result is a {\em proper} learning algorithm that learns to $\eps$-accuracy using $\tilde{O}(1/\eps^2)$ samples, and runs in time $(1/\eps)^{\poly (\log (1/\eps))} \cdot \log n$. This is nearly optimal, since any algorithm {for this problem} must use $\Omega(1/\eps^2)$ samples. We also give positive and negative results for some extensions of this learning problem to weighted sums of independent Bernoulli random variables.
Keywords
All Related Versions
This publication has 27 references indexed in Scilit:
- Sparse covers for sums of indicatorsProbability Theory and Related Fields, 2014
- Learning k-Modal Distributions via Testing2012
- Polynomial Learning of Distribution Families2010
- Settling the Polynomial Learnability of Mixtures of Gaussians2010
- Concentration of Measure for the Analysis of Randomized Algorithms2009
- An Efficient PTAS for Two-Strategy Anonymous GamesLecture Notes in Computer Science, 2008
- Probability and Statistics for Computer Science1997
- Faster computation of Bernoulli numbersJournal of Algorithms, 1992
- Binomial approximation to the Poisson binomial distributionStatistics & Probability Letters, 1991
- Schnelle Multiplikation großer ZahlenComputing, 1971