Near-optimal-sample estimators for spherical Gaussian mixtures

02/19/2014
by   Jayadev Acharya, et al.
0

Statistical and machine-learning algorithms are frequently applied to high-dimensional data. In many of these applications data is scarce, and often much more costly than computation time. We provide the first sample-efficient polynomial-time estimator for high-dimensional spherical Gaussian mixtures. For mixtures of any k d-dimensional spherical Gaussians, we derive an intuitive spectral-estimator that uses O_k(d^2d/ϵ^4) samples and runs in time O_k,ϵ(d^3^5 d), both significantly lower than previously known. The constant factor O_k is polynomial for sample complexity and is exponential for the time complexity, again much smaller than what was previously known. We also show that Ω_k(d/ϵ^2) samples are needed for any algorithm. Hence the sample complexity is near-optimal in the number of dimensions. We also derive a simple estimator for one-dimensional mixtures that uses O(k k/ϵ/ϵ^2) samples and runs in time O((k/ϵ)^3k+1). Our other technical contributions include a faster algorithm for choosing a density estimate from a set of distributions, that minimizes the ℓ_1 distance to an unknown underlying distribution.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/20/2017

List-Decodable Robust Mean Estimation and Learning Mixtures of Spherical Gaussians

We study the problem of list-decodable Gaussian mean estimation and the ...
research
02/23/2018

Fast and Sample Near-Optimal Algorithms for Learning Multidimensional Histograms

We study the problem of robustly learning multi-dimensional histograms. ...
research
06/09/2013

Minimax Theory for High-dimensional Gaussian Mixtures with Sparse Mean Separation

While several papers have investigated computationally and statistically...
research
12/14/2020

Small Covers for Near-Zero Sets of Polynomials and Learning Latent Variable Models

Let V be any vector space of multivariate degree-d homogeneous polynomia...
research
06/18/2021

VSAC: Efficient and Accurate Estimator for H and F

We present VSAC, a RANSAC-type robust estimator with a number of novelti...
research
12/16/2019

Learning Mixtures of Linear Regressions in Subexponential Time via Fourier Moments

We consider the problem of learning a mixture of linear regressions (MLR...
research
04/13/2020

Learning Mixtures of Spherical Gaussians via Fourier Analysis

Suppose that we are given independent, identically distributed samples x...

Please sign up or login with your details

Forgot password? Click here to reset