Gaussian Mixture

Gaussian Mixture Models (GMMs) are probabilistic models representing data as a weighted sum of Gaussian distributions, aiming to capture complex, multimodal data distributions. Current research focuses on improving parameter estimation efficiency, particularly for high-dimensional data and large numbers of components, often employing Expectation-Maximization (EM) algorithms, sometimes with method-of-moments warm starts, and exploring alternative approaches like diffusion models and optimal transport. These advancements are crucial for applications ranging from medical image segmentation and anomaly detection to robotics and time series forecasting, where accurately modeling complex data distributions is essential for robust and reliable results.

Papers

November 7, 2024

Non-Euclidean Mixture Model for Social Network Embedding
Roshni G. Iyer, Yewen Wang, Wei Wang, Yizhou Sun
Graph Representation Learning Social Network Node Embeddings Gaussian Mixture Graph Embeddings Event Linking Network Formation

November 1, 2024

Magnitude Pruning of Large Pretrained Transformer Models with a Mixture Gaussian Prior
Mingxuan Zhang, Yan Sun, Faming Liang
Language Understanding Mixture Component Gaussian Mixture Sparse Transformer Magnitude Pruning Large Pre Trained Transformer Gaussian Prior Magnitude Based Pruning

October 30, 2024

ELBOing Stein: Variational Bayes with Stein Mixture Inference
Ola Rønning, Eric Nalisnick, Christophe Ley, Padhraic Smyth, Thomas Hamelryck
Monte Carlo Gaussian Mixture Approximate Bayesian Inference Variational Bayes Variational Bayesian Inference

October 16, 2024

Tuning Language Models by Mixture-of-Depths Ensemble
Haoyan Luo, Lucia Specia
Gaussian Mixture Transformer Based Large Language Model Language Modeling Task Depth Anything

October 15, 2024

On the Training Convergence of Transformers for In-Context Classification
Wei Shen, Ruida Zhou, Jing Yang, Cong Shen
Transformer Megatron Decepticons Classification Code Transformer Based Training Dynamic Gaussian Mixture Different Context Training Convergence

October 9, 2024

Gem: Gaussian Mixture Model Embeddings for Numerical Feature Distributions
Hafiz Tayyab Rauf, Alex Bogatu, Norman W. Paton, Andre Freitas
Jina Embeddings Gaussian Mixture Model Gaussian Mixture Categorical Data Feature Distribution

October 8, 2024

The Breakdown of Gaussian Universality in Classification of High-dimensional Mixtures
Xiaoyi Mai, Zhenyu Liao
Classification Code Gaussian Mixture Gaussian Model Gaussian Data Dimensional Gaussian Mixture Gaussian Universality

September 16, 2024

Learning large softmax mixtures with warm start EM
Xin Bing, Florentina Bunea, Jonathan Niles-Weed, Marten Wegkamp
Softmax Function Expectation Maximization Mixture Model Gaussian Mixture Multinomial Logit Mixture Permutation

August 19, 2024

Confirmation Bias in Gaussian Mixture Models
Amnon Balanov, Tamir Bendory, Wasim Huleihel
Gaussian Mixture Model Gaussian Mixture Noisy Observation Confirmation Bias

August 9, 2024

GuidedNet: Semi-Supervised Multi-Organ Segmentation via Labeled Data Guide Unlabeled Data
Haochen Zhao, Hui Meng, Deqian Yang, Xiaozheng Xie, Xiaoze Wu, Qingfeng Li, Jianwei Niu
Semi Supervised Gaussian Mixture Multi Organ Segmentation Guided Network Organ Annotation

July 29, 2024

Online Multi-Source Domain Adaptation through Gaussian Mixtures and Dataset Dictionary Learning
Eduardo Fernandes Montesuma, Stevan Le Stanc, Fred Ngolè Mboula
Transfer Learning Gaussian Mixture Model Gaussian Mixture Multi Source Domain Adaptation Heterogeneous Domain Dataset Dictionary Learning

June 29, 2024

Toward Global Convergence of Gradient EM for Over-Parameterized Gaussian Mixture Models
Weihang Xu, Maryam Fazel, Simon S. Du
Gaussian Mixture Model Expectation Maximization Gaussian Mixture Global Convergence

June 25, 2024

Efficient, Multimodal, and Derivative-Free Bayesian Inference With Fisher-Rao Gradient Flows
Yifan Chen, Daniel Zhengyu Huang, Jiaoyang Huang, Sebastian Reich, Andrew M. Stuart
High Efficiency Inverse Problem Multimodal Phenomenon Bayesian Inference Gaussian Mixture Fisher Rao Gradient Flow

June 13, 2024

Weakly-supervised anomaly detection for multimodal data distributions
Xu Tan, Junqi Chen, Sylwan Rahardja, Jiawei Yang, Susanto Rahardja
Gaussian Mixture Anomaly Score Multimodal Distribution Weakly Supervised Anomaly Detection

June 3, 2024

Tilting the Odds at the Lottery: the Interplay of Overparameterisation and Curricula in Neural Networks
Stefano Sarao Mannelli, Yaraslau Ivashynka, Andrew Saxe, Luca Saglietti
Neural Network Deep Learning Gaussian Mixture Deep Learning Application Lottery Ticket Overparametrization Bound Relative Probability

May 26, 2024

Unraveling the Smoothness Properties of Diffusion Models: A Gaussian Mixture Perspective
Yingyu Liang, Zhenmei Shi, Zhao Song, Yufa Zhou
Diffusion Model Gaussian Mixture Diffusion Process Smoothness Assumption Diffusion Solver Smooth Density

May 22, 2024

Adaptive Fuzzy C-Means with Graph Embedding
Qiang Chen, Weizhong Yu, Feiping Nie, Xuelong Li
Graph Drawing Gaussian Mixture Model Gaussian Mixture Fuzzy C Mean Fuzzy Clustering

May 6, 2024

sc-OTGM: Single-Cell Perturbation Modeling by Solving Optimal Mass Transport on the Manifold of Gaussian Mixtures
Andac Demir, Elizaveta Solovyeva, James Boylan, Mei Xiao, Fabrizio Serluca, Sebastian Hoersch, Jeremy Jenkins, Murthy Devarakonda, Bulent Kiziltan
Gaussian Mixture Dimensional Manifold scRNA Seq Single Cell Data Perturbation Analysis Genetic Perturbation Optimal Mass Transport Cell Nucleus

May 1, 2024

Gaussian Universality in Neural Network Dynamics with Generalized Structured Input Distributions
Jaeyong Bae, Hawoong Jeong
Deep Learning Gaussian Mixture K$ Universality Empirical Evidence Neural Network Dynamic

April 29, 2024

Learning general Gaussian mixtures with efficient score matching
Sitan Chen, Vasilis Kontonis, Kulin Shah
LeArning Abstract Gaussian Mixture Covariance Matrix Score Matching O$ Sample

Gaussian Mixture

Papers

Non-Euclidean Mixture Model for Social Network Embedding

Magnitude Pruning of Large Pretrained Transformer Models with a Mixture Gaussian Prior

ELBOing Stein: Variational Bayes with Stein Mixture Inference

Tuning Language Models by Mixture-of-Depths Ensemble

On the Training Convergence of Transformers for In-Context Classification

Gem: Gaussian Mixture Model Embeddings for Numerical Feature Distributions

The Breakdown of Gaussian Universality in Classification of High-dimensional Mixtures

Learning large softmax mixtures with warm start EM

Confirmation Bias in Gaussian Mixture Models

GuidedNet: Semi-Supervised Multi-Organ Segmentation via Labeled Data Guide Unlabeled Data

Online Multi-Source Domain Adaptation through Gaussian Mixtures and Dataset Dictionary Learning

Toward Global Convergence of Gradient EM for Over-Parameterized Gaussian Mixture Models

Efficient, Multimodal, and Derivative-Free Bayesian Inference With Fisher-Rao Gradient Flows

Weakly-supervised anomaly detection for multimodal data distributions

Tilting the Odds at the Lottery: the Interplay of Overparameterisation and Curricula in Neural Networks

Unraveling the Smoothness Properties of Diffusion Models: A Gaussian Mixture Perspective

Adaptive Fuzzy C-Means with Graph Embedding

sc-OTGM: Single-Cell Perturbation Modeling by Solving Optimal Mass Transport on the Manifold of Gaussian Mixtures

Gaussian Universality in Neural Network Dynamics with Generalized Structured Input Distributions

Learning general Gaussian mixtures with efficient score matching