ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 1905.08448
10
28

Efficient Profile Maximum Likelihood for Universal Symmetric Property Estimation

21 May 2019
Moses Charikar
Kirankumar Shiragur
Aaron Sidford
ArXivPDFHTML
Abstract

Estimating symmetric properties of a distribution, e.g. support size, coverage, entropy, distance to uniformity, are among the most fundamental problems in algorithmic statistics. While each of these properties have been studied extensively and separate optimal estimators are known for each, in striking recent work, Acharya et al. 2016 showed that there is a single estimator that is competitive for all symmetric properties. This work proved that computing the distribution that approximately maximizes \emph{profile likelihood (PML)}, i.e. the probability of observed frequency of frequencies, and returning the value of the property on this distribution is sample competitive with respect to a broad class of estimators of symmetric properties. Further, they showed that even computing an approximation of the PML suffices to achieve such a universal plug-in estimator. Unfortunately, prior to this work there was no known polynomial time algorithm to compute an approximate PML and it was open to obtain a polynomial time universal plug-in estimator through the use of approximate PML. In this paper we provide a algorithm (in number of samples) that, given nnn samples from a distribution, computes an approximate PML distribution up to a multiplicative error of exp⁡(n2/3polylog⁡(n))\exp(n^{2/3} \mathrm{poly} \log(n))exp(n2/3polylog(n)) in time nearly linear in nnn. Generalizing work of Acharya et al. 2016 on the utility of approximate PML we show that our algorithm provides a nearly linear time universal plug-in estimator for all symmetric functions up to accuracy ϵ=Ω(n−0.166)\epsilon = \Omega(n^{-0.166})ϵ=Ω(n−0.166). Further, we show how to extend our work to provide efficient polynomial-time algorithms for computing a ddd-dimensional generalization of PML (for constant ddd) that allows for universal plug-in estimation of symmetric relationships between distributions.

View on arXiv
Comments on this paper