English

Distribution Compression in Near-linear Time

Machine Learning 2022-10-19 v6 Data Structures and Algorithms Machine Learning Statistics Theory Methodology Statistics Theory

Abstract

In distribution compression, one aims to accurately summarize a probability distribution P\mathbb{P} using a small number of representative points. Near-optimal thinning procedures achieve this goal by sampling nn points from a Markov chain and identifying n\sqrt{n} points with O~(1/n)\widetilde{\mathcal{O}}(1/\sqrt{n}) discrepancy to P\mathbb{P}. Unfortunately, these algorithms suffer from quadratic or super-quadratic runtime in the sample size nn. To address this deficiency, we introduce Compress++, a simple meta-procedure for speeding up any thinning algorithm while suffering at most a factor of 44 in error. When combined with the quadratic-time kernel halving and kernel thinning algorithms of Dwivedi and Mackey (2021), Compress++ delivers n\sqrt{n} points with O(logn/n)\mathcal{O}(\sqrt{\log n/n}) integration error and better-than-Monte-Carlo maximum mean discrepancy in O(nlog3n)\mathcal{O}(n \log^3 n) time and O(nlog2n)\mathcal{O}( \sqrt{n} \log^2 n ) space. Moreover, Compress++ enjoys the same near-linear runtime given any quadratic-time input and reduces the runtime of super-quadratic algorithms by a square-root factor. In our benchmarks with high-dimensional Monte Carlo samples and Markov chains targeting challenging differential equation posteriors, Compress++ matches or nearly matches the accuracy of its input algorithm in orders of magnitude less time.

Keywords

Cite

@article{arxiv.2111.07941,
  title  = {Distribution Compression in Near-linear Time},
  author = {Abhishek Shetty and Raaz Dwivedi and Lester Mackey},
  journal= {arXiv preprint arXiv:2111.07941},
  year   = {2022}
}

Comments

Accepted to ICLR 2022; An outdated proof of Theorem 2 was previously included in the appendix; this oversight is corrected in this version

R2 v1 2026-06-24T07:39:15.632Z