← Back to all news
arXiv Machine Learning By Yiran Zhang, Mo Zhou, Weihang Xu, Maryam Fazel, Simon S. Du

Is $\sqrt{d}$ Separation Necessary for Gradient EM to Learn Gaussian Mixtures in High Dimensions?

Read the original on arXiv Machine Learning →

arXiv:2610. 07551v1 Announce Type: cross Abstract: Learning Gaussian mixture models (GMMs) using the Expectation-Maximization (EM) algorithm and its gradient-based variants is a fundamental problem in machine learning.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Aug 19

Global Convergence of Gradient EM for Over-Parameterized Gaussian Mixtures

arXiv:2506. 06584v2 Announce Type: replace Abstract: Learning Gaussian Mixture Models (GMMs) is a fundamental problem in statistics and machine learning, with the Expectation-Maximization (EM) algorithm and its popular variant gradient EM being arguably the most widely used algorithms in practice.

By Mo Zhou, Weihang Xu, Maryam Fazel, Simon S. Du
More like this →
arXiv Machine Learning
Sep 11

Sublinear Variational Optimization of Gaussian Mixture Models with Millions to Billions of Parameters

The paper introduces a highly efficient variational approximation for Gaussian Mixture Models (GMMs) with arbitrary covariances, integrated with mixtures of factor analyzers. This method reduces the per‑iteration runtime from ≠O(NCD^2) to a complexity that scales linearly with dimensionality D and sublinearly with the product NC. Experiments demonstrate sublinear scaling across the entire optimization, order‑of‑magnitude speed‑ups on large benchmarks, training of GMMs with over 10 billion parameters in under nine hours on a single CPU, and competitive zero‑shot image denoising performance.

By Sebastian Salwig, Till Kahlke, Florian Hirschberger, Dennis Forster, J\"org L\"ucke
benchmarks
More like this →
arXiv Machine Learning
Sep 10

The EM-algorithm and the Method of Moments in Softmax Mixture Models

arXiv:2409. 09903v3 Announce Type: replace-cross Abstract: Softmax Mixture Models (SMMs) are discrete $K$-component mixture models for the probabilities of selecting one of $p$ candidate feature vectors $X_1,\ldots,X_p\in\mathbb{R}^L$ in heterogeneous populations and are widely used in econometrics and scientific applications.

By Xin Bing, Florentina Bunea, Jonathan Niles-Weed, Marten Wegkamp
llms
More like this →