Expectation-Maximization

Also known as EM

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 19

All topics

Is $\sqrt{d}$ Separation Necessary for Gradient EM to Learn Gaussian Mixtures in High Dimensions?
Oct 6, 2026Yiran Zhang, Mo Zhou, Weihang Xu +2Gaussian Mixture Models Expectation-Maximization
University of California, Berkeley · University of Washington · Amazon, Inc.
Joint Estimation of Common-Slope Decay Rates and Spatial Amplitudes Using Parameterized Nonnegative Matrix Factorization
Oct 4, 2026Jeremy B. Bai, Filip Elvander, Sebastian J. SchlechtNon-Negative Matrix Factorization Expectation-Maximization
Multimedia Comms. & Signal Proc., Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany · Dept. of Information and Communications Engineering, Aalto University, Finland
Statistical Rates for Entropic Optimal Transport in the Discrete to SubGaussian Regime
Sep 22, 2026Tomas Gonzalez, Gonzalo MenaExpectation-Maximization Optimal Transport
Department of Machine Learning, Carnegie Mellon University · Department of Statistics & Data Science, Carnegie Mellon University
Impute-EM: Native Mixed-State Diffusion Models for Heterogeneous Data Imputation
Sep 14, 2026Sergei Kholkin, Kirill Sokolov, Dmitry Baranchuk +2Incomplete Data Imputation Expectation-Maximization
Applied AI Institute · Applied AI Institute, Moscow State University · Yandex Research +1
Structure Aware Neural Architecture Search for Mixture of Experts
Aug 30, 2026Petr Babkin, Oleg BakhteevExpectation-Maximization Neural Architecture Search
Estimation, Prediction, and Assortment Optimization for Markov Chain Choice Models with Panel Data
Jul 10, 2026Yalcin Akcay, Gerardo Berbeglia, Young-San LinExpectation-Maximization Discrete Choice Modeling
Melbourne Business School
Stochastic Expectation Maximization for Robust State-Space Radio Interferometric Imaging
Jun 22, 2026Nawel Arab, Mohammed Nabil El Korso, Isabelle Vin +1Image Reconstruction Expectation-Maximization
†SATIE, ENS Paris-Saclay, Universit´e Paris-Saclay, France · ‡L2S, CentraleSupelec, Universit´e Paris-Saclay, France
EM-NeSy: Expectation Maximization for Neurosymbolic Learning
Jun 12, 2026Annegret Seibt, Luc De Raedt, Giuseppe MarraSymbolic Reasoning Expectation-Maximization
Department of Computer Science KU Leuven
libhmm: A Modern C++20 Library for Hidden Markov Models with Correct MLE Emission M-Steps
May 28, 2026Gary WolfmanParameter Estimation Markov Models
Independent Researcher
Higher-Order Equilibrium Tracking for EM-Compressible Online Estimation
May 9, 2026ZhiMing Li, Yue SongLatent Variable Models Stochastic Approximation
School of Computer Science and Technology TianJin University Tianjin 300350, China · College of AI Tsinghua University Beijing 100084, China
Online Generalised Predictive Coding
May 4, 2026Mehran H. Z. Bazargani, Szymon Urbas, Adeel Razi +2Parameter Estimation Latent Dynamics Modeling
Insight Research Ireland Centre, UCD, Dublin, Ireland. · UCD School of Mathematics and Statistics, UCD, Belfield, Dublin, Ireland. · Turner Institute for Brain and Mental Health, School of Psychological Sciences, Monash University, Melbourne, Victoria, Australia. +5
Fitting Large Nonlinear Mixed Effects Models Using Variational Expectation Maximization
Apr 28, 2026Mohamed Tarek, Pedro AfonsoExpectation-Maximization Variational Inference
PumasAI, USA
Fractionally Supervised Classification with Maxima Nominated Samples
Apr 28, 2026Mohammad Jafari Jozani, Jingyu WangLatent Variable Models Expectation-Maximization
Department of Statistics, University of Manitoba, Winnipeg, MB, Canada · RBC Capital Markets, Toronto, Canada
Gradient Descent as Implicit EM in Distance-Based Neural Models
Dec 31, 2025Alan OurslandExpectation-Maximization Neural Network Training Dynamics
Differentiable Expectation-Maximisation and Applications to Gaussian Mixture Model Optimal Transport
Sep 2, 2025Samuel Boïté, Eloi Tanguy, Julie Delon +2Gaussian Mixture Models Expectation-Maximization
Université Paris Cité, CNRS, MAP5, F-75006 Paris, France · Centre Borelli, CNRS and ENS Paris-Saclay, F-91190 Gif-sur-Yvette, France · CMAP, CNRS, Ecole Polytechnique, Institut Polytechnique de Paris
FastManly: An EM-Gradient Algorithm for Manly Mixture Models
Oct 1, 2024Katharine M. Clark, Paul D. McNicholasParameter Estimation Expectation-Maximization
Department of Mathematics & Statistics, Trent University, Ontario, Canada. · Department of Mathematics & Statistics, McMaster University, Ontario, Canada.
The EM-algorithm and the Method of Moments in Softmax Mixture Models
Sep 16, 2024Xin Bing, Florentina Bunea, Jonathan Niles-Weed +1Expectation-Maximization Discrete Choice Modeling
Department of Statistical Sciences, University of Toronto · Department of Statistics and Data Science, Cornell University · Courant Institute of Mathematical Sciences and Center for Data Science, New York University +1
An Expectation-Maximization Algorithm for Training Clean Diffusion Models from Corrupted Observations
Jul 1, 2024Weimin Bai, Yifei Wang, Wenzheng Chen +1Expectation-Maximization Diffusion-Based Inverse Problems
Academy for Advanced Interdisciplinary Studies, Peking University · College of Future Technology, Peking University · National Biomedical Imaging Center, Peking University +3
Regularized Estimation and Feature Selection in Mixtures of Generalized Linear Experts
Jul 14, 2019Thin Nguyen-Van, Faicel Chamroukhi, Ha Hoang Van +1Mixture of Experts Sparse Mixture-of-Experts
Faculty of Mathematics and Computer Science, University of Science, Ho Chi Minh City, Vietnam · Vietnam National University, Ho Chi Minh City, Vietnam · IRT SystemX, 91120 Palaiseau, France +1

Oct 6, 2026, stat.MLJ/K move · Enter open · S save

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

Yiran Zhang, Mo Zhou, Weihang Xu, Maryam Fazel+1

University of California, Berkeley · University of Washington · Amazon, Inc.

Gaussian Mixture Models Expectation-Maximization Statistical Learning Theory

Open paper AskPDF arXiv

Learning Gaussian mixture models (GMMs) using the Expectation-Maximization (EM) algorithm and its gradient-based variants is a fundamental problem in machine learning. It is known that randomly initialized (gradient) EM fails to learn multi-component GMMs in the exact-parameterized setting, where the number of components matches that of the ground-truth GMM. Recently, global convergence of gradient EM has been established in the over-parameterized setting, where more components are used, provided that the ground-truth components are well separated. In particular, the minimum separation between ground-truth components is required to scale as

Ω(\sqrt{d})

, where

d

is the dimension. In this paper, we show that this dimensional dependence is unavoidable in high-dimensional settings. Specifically, we consider a hybrid EM algorithm that uses standard EM updates for the mixing weights and gradient EM updates for the component means. For any

ε> 0

, we prove that when the dimension is sufficiently large, in the worst case a separation of order

Ω(d^{0.5-ε})

is insufficient to guarantee global convergence of population gradient EM in sub-exponential time under random initialization, even in the over-parameterized regime. Our result establishes an almost optimal worst-case lower bound on the ground-truth separation required for learning Gaussian mixtures via gradient EM in high dimensions.

Momentum

Related topics

Latest papers 19