Gaussian Mixture Models

Follow this topic Ask about this topic

Momentum

7 papers in the last four weeks, up 40% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 81

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 High-Dimensional
University of California, Berkeley · University of Washington · Amazon, Inc.
Polylogarithmic Sparsity of Randomly Reweighted NPMLEs for Gaussian Mixtures
Oct 1, 2026Hansheng JiangMaximum Likelihood Gaussian Mixture Models
University of Toronto
Correcting CondOT: Exact Finite-Step Sampling in Gaussian Flow Matching
Sep 30, 2026Ron Levy, Michael EladConditional Flow Matching Rejection Sampling
Department of Computer Science Technion, Israel
Anisotropic Representations Improve Planning in JEPA World Models
Sep 29, 2026Mingu Kang, Yoori Oh, Sookyung Kim +1Latent World Models Low-Latency Latent Planning
Seoul National University · Ewha Womans University
ProtoSeam: Lifting Classifier Training with Latent Gaussian Mixture Models
Sep 28, 2026Robert Lampel, Timon Klein, Sebastian SagerLearnable Prototypes Classifier
Department of Mathematics, Otto von Guericke University (Magdeburg, Germany) · Max Planck Institute for Dynamics of Complex Technical Systems (Magdeburg, Germany)
Exact Bayes Regret and Asymptotic Optimality in High-Dimensional Gaussian Bandits
Sep 23, 2026Prakhar Singhvi, Yi Zou, Abhishek BhattacharjeeInterval Regret Gaussian Mixture Models
Abstract Math Institute
Federated Soft Clustering via Generalized Total Variation Minimization
Sep 16, 2026Shamsiiat Abdurakhmanova, Alexander JungClustering Gaussian Mixture Models
Department of Computer Science, Aalto University, Espoo, Finland
SGD in Multiclass Logistic Regression: Sequential Learning and Scaling Laws
Sep 7, 2026Konstantinos Christopher Tsiolis, Denny Wu, Christos Thrampoulidis +1Logistic Regression Multiclass Classification
University of Toronto, Vector Institute · New York University, Flatiron Institute · University of British Columbia +1
Hessian-based molecular conformation augmentation for a scalable and efficient strategy of machine learning interatomic potentials
Sep 4, 2026Bumju Kwak, Jeonghee JoInteratomic Potentials Conformational Ensembles
Independent researcher, Seoul, Republic of Korea
Geometric Ceilings on Time-Frequency Masking for Single-Channel Separation
Sep 3, 2026Maxime BaeldeSpeech Separation Time-Frequency
Independent researcher, Lille, France
Cluster Assignments in Soft Targets Shape Speech Representations: Evidence from S-JEPA
Aug 19, 2026Wenxuan He, Yunpeng Li, Zewei Li +4Self-Supervised Speech Models Discrete Speech Representations
Department of Intelligent Science, School of Advanced Technology, Xi’an Jiaotong-Liverpool University, Suzhou, China
VIScore: Diagnosing Planning-Relevant Quality in Latent World Models
Aug 11, 2026Haiyu Wu, Randall Balestriero, Morgan LevineLatent World Models World Model Planning
Altos Labs · Brown University
Dynamic Distribution-Aware Uncertainty Tracking in Vision-Language Representation Learning
Aug 10, 2026Ao Zhou, Zhiwei Jiang, Zifeng Cheng +4Recent Vision-Language Models Uncertainty
State Key Laboratory of Novel Software Technology, Nanjing University
SDDBMs: Soft Denoising Diffusion Bridge Models
Aug 9, 2026Shiyi Qi, Kun He, Mingmou LiuDiffusion Bridges Denoising Diffusion Probabilistic Model
Nanjing University · Renmin University of China
Mixture of Geodesic Factor Analyzers on Riemannian Homogeneous Spaces
Aug 7, 2026Hengchao Chen, Yuanyao Tan, Chao Huang +2Gaussian Mixture Models Riemannian Manifolds
University of Toronto · Florida State University · Eli Lilly and Company +3
Minimax Optimal Early-Stopped Gradient Descent for Gaussian Mixture Classification
Aug 6, 2026Alex Buna, Shirley Xiaoqi Liu, Patrick RebeschiniEmpirical Risk Minimization Gaussian Mixture Models
Department of Statistics, University of Oxford
Variational Bounds for Perceptron Learning from Structured Data
Aug 5, 2026Francesco Camilli, Pierluigi Contucci, Federica Gerace +1Log-Concave Distributions Upper Bounds
Department of Mathematics, Alma Mater Studiorum – Universit`a di Bologna, Piazza di Porta San Donato 5, 40126 Bologna, Italy
Attention-Only White-Box Transformer via LeJEPA-Based Self-Supervised Pretraining
Aug 4, 2026Yang Bai, Linyuan Wang, Haoyang Jiang +3Transformer Attention Self-Supervised Learning
Information Engineering University, ZhengZhou,China
Rethinking Likelihood distributions: Student's t Likelihood Boosts Bayesian Neural Network Performance
Jul 28, 2026Pei-Hsuan Hsia, Lars H. Heyen, Arvid Weyrauch +4Bayesian Neural Networks Variational Inference
Scientific Computing Center, Karlsruhe Institute of Technology · Scientific Computing Center, Karlsruhe Institute of Technology; and Helmholtz AI
Lloyd's $K$ -Means Clustering Algorithm Is Frank-Wolfe in Disguise
Jul 28, 2026Michael Pokojovy, J. Marcus Jobe, Simon Lacoste-JulienK-Means Convex Optimization
Department of Mathematics & Statistics and School of Data Science Old Dominion University Norfolk, VA 23529, USA · Information Systems & Analytics Department Miami University Oxford, OH 45056, USA · Canada CIFAR AI Chair Department of Computer Science and Operations Research & Mila Université de Montréal Montréal (QC) Canada
Variational Quantum Conditional Boltzmann Machines for Time-Series Forecasting: Architectures, Symmetric Hyperparameter Evaluation, and a Nonlinear Benchmark
Jul 27, 2026Gerhard Hellstern, Danyal Maheshwari, Martin Zaefferer +2Hybrid Quantum-Classical Pipeline Time Series Forecasting
Centre of Finance DHBW Stuttgart Stuttgart, Germany · Zentrum für Digitale Innovationen DHBW Ravensburg Ravensburg, Germany · DATEV eG Nürnberg, Germany
Fundamental limits of distributed multiclass classification from simple binary decisions
Jul 21, 2026Ioannis Papageorgiou, Srinivas Nomula, Ayalvadi Ganesh +2Multiclass Classification Gaussian Mixture Models
School of Mathematics, University of Bristol · Department of Electrical Communication Engineering, Indian Institute of Science.
RayOcc: Occlusion-Aware Ray Occupancy Estimation via Gaussian Mixture Intensity
Jul 20, 2026Junho Kim, Seongwon Lee3D Semantic Occupancy Prediction Occupancy
School of Electrical Engineering, Kookmin University, Seoul 02707, South Korea
Robust Chance-Constrained Optimization using a Continuous Parameter Space Wasserstein-2 Ambiguity Set of Gaussian Mixtures
Jul 19, 2026Shibshankar Dey, Sanjay MehrotraDistributionally-Robust Optimization Robust Optimization
Department of Industrial Engineering and Management Sciences, Northwestern University
Dimension-Calibrated Unexplained Mass: An Interpretable Drift Statistic for Contamination Monitoring in Data Streams
Jul 18, 2026Behnam AsadiGaussian Mixture Models Unsupervised Detection
Spectral Concentration and Recovery in Sparse High-Dimensional Random Geometric Graphs
Jul 15, 2026Manuel Fernandez, Yizhe ZhuInhomogeneous Random Graphs Discriminative Congruence Transform
Department of Mathematics, University of Southern California
Heavy-Tailed Flow Matching via Random Clocks
Jul 15, 2026Zhouhao Yang, Yezhen Wang, Kenji Kawaguchi +2Conditional Flow Matching Long-Tailed Distribution
Department of Applied Mathematics and Statistics, Johns Hopkins University. · School of Computing, National University of Singapore. · Department of Computer Science, Johns Hopkins University.
UD-ASD: A Unified Diffusion Model for Anomalous Sound Detection
Jul 14, 2026Pengxiang Gao, Yu Qiu, Yanzhi SongSound Event Detection Neural Audio
University of Science and Technology of China, China
Gaussian Mixture Modeling for Event-Aware Visual Allocation in Long Video Understanding
Jul 14, 2026Yifan Lu, Ziqi Zhang, Chunfeng Yuan +3Video Understanding Long Visual-Token Sequences
Beijing Key Laboratory of Super Intelligent Security of Multi-Modal Information, CASIA · State Key Laboratory of Multimodal Artificial Intelligence Systems, CASIA · School of Artificial Intelligence, University of Chinese Academy of Sciences +2
Mixture-of-Gaussians-Guided Schedule Design for Brownian Bridge Diffusion Models
Jul 3, 2026Ron Levi, Michael EladDiffusion Bridges Schrödinger Bridges
Department of Computer Science Technion, Israel
eXact-Prior Variational Autoencoder (X-VAE): Learning Data-Adaptive Gaussian Mixture Priors for Latent Distributions
Jun 30, 2026Qijun Chen, Shaofan LiConditional Variational Autoencoder Star-Vae
Department of Civil and Environmental Engineering, University of California, Berkeley, CA, 94720, USA
Multi-Contact Force Estimation for Continuum Robots via Gaussian-Parameterized Factor Graphs
Jun 28, 2026Aditya Prakash, Panagiotis TsiotrasGround Reaction Forces Cosserat Rod Theory
School of Aerospace Engineering Georgia Institute of Technology Atlanta, GA, USA
Rethinking Training & Inference for Forecasting: Linking Winner-Take-All back to GMMs
Jun 24, 2026Qiyuan Wu, Katie Z Luo, Bharath Hariharan +2Trajectory Forecasting Posterior
Cornell University · Stanford University · Boston University
From Point Estimates to Distributions: GMM Pooling for MIL in Preterm Birth Prediction
Jun 22, 2026Hussain Alasmawi, Numan Saeed, Soha Said +1Multiple Instance Learning Gaussian Mixture Models
Division of Computing and Mathematical Sciences, Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, United Arab Emirates · Corniche Hospital, Abu Dhabi Health Services Company (SEHA), Abu Dhabi, UAE
Global Convergence of Gradient Descent for Score Matching in Gaussian Mixtures via Reverse Fisher Divergence
Jun 18, 2026Alexander TyurinGaussian Mixture Models Gradient Descent
AXXX, Moscow, Russia · Applied AI Institute, Moscow, Russia
S-JEPA : Soft Clustering Anchors for Self-Supervised Speech Representation Learning
Jun 17, 2026Georgios Ioannides, Adrian Kieback, Judah Goldfeder +5S-Jepa Representation Learning
Carnegie Mellon University · James Silberrad Brown Center for AI · Amazon GenAI +4
Deep Image Prototype Learning with Geometric Heat-Kernel Priors
Jun 17, 2026Jiarui Xing, Tal Zeevi, Nian Wu +1Learnable Prototypes Latent Variable
Yale School of Medicine, New Haven CT, 06510, USA · University of Virginia, Charlottesville, VA, 22903, USA · Harvard Medical School, Boston MA, 02115, USA
Transductive Zero-Shot Audio Classification with Audio-Language Models
Jun 15, 2026Jingwen Zhou, Mingzhe WangZero-Shot Transductive Learning
Xidian University, Xi’an, China
Recursively Trained Diffusion Models: Limiting Collapse Distribution and Spectral Characterization
Jun 11, 2026Naïl B. Khelifa, Richard E. Turner, Ramji VenkataramananDiffusion Models Gaussian Mixture Models
University of Cambridge
Flash-GMM: A Memory-Efficient Kernel for Scalable Soft Clustering
Jun 9, 2026Gal Bloch, Ariel Gera, Matan Orbach +2Gaussian Mixture Models Clustering
IBM Research
SSL-GMMVC: Interpretable Voice Conversion via Locally Linear GMM Transforms in Self-Supervised Representation Space
Jun 9, 2026Tomoya Tanabu, Hiroshi Nishijima, Daisuke Saito +1Self-Supervised Speech Models Voice Conversion
The University of Tokyo, Japan
PTL-Diffusion: Manifold-Aware Diffusion with Periodic Terminal Laws
Jun 8, 2026Danqi Zhuang, Jisui Huang, Xiaoyue Xi +4Diffusion Models Gaussian Mixture Models
Department of Mathematics and Statistics, University of Strathclyde, Glasgow, UK · Centre for Mathematical Imaging Techniques and Department of Mathematical Sciences, University of Liverpool, Liverpool, UK · Department of Medical Statistics, London School of Hygiene & Tropical Medicine, London, UK +2
Beyond Self-Attention: Sub-Quadratic Vision Transformers for Fast Image Captioning
Jun 7, 2026Chiradeep Ghosh, Dakshina Ranjan KiskuSelf-Supervised Vision Transformers Vision Transformer
Department of Computer Science and Engineering · National Institute of Technology Durgapur · Durgapur, India
How abundant are good interpolators?
Jun 4, 2026August Y. Chen, Ahmed El AlaouiStochastic Interpolants Overparameterization
Cornell University, Department of Computer Science. Ithaca, NY, USA. · Cornell University, Department of Statistics and Data Science. Ithaca, NY, USA.
BPDA-GMM: Bayesian Probabilistic Data Association via Gaussian Mixture Models for Semantic SLAM
Jun 3, 2026Thanh Nguyen Canh, Haolan Zhang, Xiem HoangVan +2Simultaneous Localization And Mapping Gaussian Mixture Models
School of Information Science, Japan Advanced Institute of Science and Technology, Ishikawa, 923-1211, Japan · University of Engineering and Technology, Vietnam National University, Hanoi, 10000, Vietnam
Hierarchical GRU with Input-Conditioned Slot Queries for Ball Action Anticipation
Jun 2, 2026Parthsarthi RawatAction Prediction Gaussian Mixture Models
GameChanger by Dick’s Sporting Goods
Are we really tilting? The mechanics of reward guidance in flow and diffusion models
Jun 1, 2026Sanjit Dandapanthula, Nicholas M. BoffiReward Gradients Reward Functions
Carnegie Mellon University
UR-JEPA: Uniform Rectifiability as a Regularizer for Joint-Embedding Predictive Architectures
May 31, 2026Triet M. LeJoint-Embedding Predictive Architectures S-Jepa
Local linear convergence of gradient methods for overparameterized Gaussian mixtures
May 29, 2026Jingxing Wang, Vasileios Charisopoulos, Maryam FazelGaussian Mixture Models Overparameterization
Electrical & Computer Engineering, University of Washington, Seattle, WA · National Institute for Theory and Mathematics in Biology, Chicago, IL · Amazon, Inc.
Diffusion Models Are Statistically Optimal for Learning Low-Dimensional Multi-Modal Distributions
May 28, 2026Jingda Wu, Changxiao CaiLow-Dimensional Structure Score-Based Diffusion Model
Department of Industrial and Operations Engineering, University of Michigan, Ann Arbor, USA.
Robust Moment-Based Estimation via Spectral Gradient Reweighting
May 26, 2026Liu Zhang, Amit SingerGaussian Mixture Models Stochastic Gradient Descent
Program in Applied and Computational Mathematics, Princeton University, Princeton, NJ 08544 USA · Department of Mathematics and Program in Applied and Computational Mathematics, Princeton University, Princeton, NJ 08544 USA
Certified Robustness from Approximate Gaussian Mixture Structures in Pretrained Latent Spaces
May 25, 2026Konstantinos Emmanouilidis, Tianjiao Ding, Nghia Nguyen +2Adversarial Training Robustness Verification
CS & MINDS Johns Hopkins University · CIS University of Pennsylvania
Optimizing Multidimensional Scaling in Gini Metric Spaces
May 24, 2026Cassandra Mussard, Stéphane MussardMetric Spaces Gaussian Mixture Models
CESBIO, Univ. Toulouse Toulouse, France · CHROME, Univ. Nˆımes UM6P, AIRESS Nˆımes, France
Lifted Schrödinger Bridges for Gaussian Mixture Endpoints: Projection Gaps and Path-Space Obstructions
May 24, 2026Siddhartha Ganguly, George Rapakoulias, Panagiotis TsiotrasSchrödinger Bridges Gaussian Mixture Models
S. Ganguly, G. Rapakoulias, and P. Tsiotras are with Daniel Guggenheim School of Aerospace, Georgia Institute of Technology, ½ Atlanta, USA.
DiffCVaR: Reinforcement Learning for Risk Adaptation via Differentiable CVaR Barrier Functions
May 20, 2026Xinyi Wang, Taekyung Kim, Bardh Hoxha +2Obstacle Avoidance Offline Reinforcement Learning
Department of Robotics, University of Michigan, Ann Arbor, MI, 48109, USA · Toyota Motor North America, Research & Development, Ann Arbor, MI, 48105, USA · Department of Aerospace Engineering, University of Michigan, Ann Arbor, MI, 48109, USA
Robust Recommendation from Noisy Implicit Feedback: A GMM-Weighted Bayes-label Transition Matrix Framework
May 20, 2026Zongyu Li, Xuanyu Liu, Gongce Cao +3Noisy Labels Gaussian Mixture Models
Guangdong University of Technology, Guangzhou, China · University of Chinese Academy of Sciences, Beijing, China · Capital Normal University, Dalian, China +2
A Semantic and Occlusion-Aware GM-PHD Filter
May 20, 2026Jovan Menezes, Mark CampbellMulti-Object Tracking Autonomous Driving
Sibley School of Mechanical and Aerospace Engineering, Cornell University, Ithaca, NY, USA
From Simple to Complex: Curriculum-Guided Physics-Informed Neural Networks via Gaussian Mixture Models
May 19, 2026Jianan Yang, Yiran Wang, Shuai Li +3Parametric Physics-Informed Neural Network Neural Network
Xi’an Jiaotong University, Xi’an, China · College of International Business, Zhejiang Yuexiu University, Shaoxing, China · Shaoxing Key Laboratory of Intelligent Monitoring and Prevention of Smart Society, Shaoxing, China +1
Privacy Policy Enforcement Guardrails for Data-Sensitive Retrieval-Augmented Generation
May 16, 2026Osama Zafar, Alexander Nemecek, Yiqian Zhang +5Privacy Streaming Guardrails
Dept. of Computer and Data Sciences Case Western Reserve University Cleveland, USA
Dimension-Uniform Discretization Analysis of Preconditioned Annealed Langevin Dynamics for Multimodal Gaussian Mixtures
May 15, 2026Lorenzo Baldassari, Josselin Garnier, Knut Solna +1Langevin Dynamics Diffusion Sampling
University of Basel · Ecole Polytechnique, IP Paris · University of California Irvine +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 High-Dimensional

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 81