Finite Mixture

Finite mixture models aim to represent data as a combination of several underlying probability distributions, enabling the identification of distinct subgroups or clusters within a dataset. Current research focuses on improving the robustness and efficiency of these models, particularly through the development of Byzantine-tolerant algorithms for distributed learning and refined variational inference techniques for non-Gaussian mixtures. These advancements are crucial for addressing challenges in high-dimensional data analysis, particularly in applications like machine learning, where accurate and efficient clustering is essential for tasks such as anomaly detection and personalized recommendations. Furthermore, ongoing work explores the theoretical limits of identifiability and approximation accuracy in finite mixture models, leading to improved algorithms and a deeper understanding of their capabilities.

Papers

July 19, 2024

Byzantine-tolerant distributed learning of finite mixture models
Qiong Zhang, Jiahua Chen
LeArning Abstract Split Learning Byzantine Robust Finite Mixture Byzantine Failure

June 6, 2024

Theoretical Guarantees for Variational Inference with Fixed-Variance Mixture of Gaussians
Tom Huix, Anna Korba, Alain Durmus, Eric Moulines
Variational Inference Bayesian Inference RSD Difference of Gaussian Posterior Inference Gaussian Kernel Theoretical Guarantee Finite Mixture

April 13, 2024

On the best approximation by finite Gaussian mixtures
Yun Ma, Yihong Wu, Pengkun Yang
Average Approximation Low Rank Approximation Spectral Analysis Approximation Error Finite Mixture

March 27, 2024

Clustering Change Sign Detection by Fusing Mixture Complexity
Kento Urano, Ryo Yuki, Kenji Yamanishi
Gaussian Mixture Model Cluster Structure Input Mixture Finite Mixture

October 30, 2023

Improved Bayesian Regret Bounds for Thompson Sampling in Reinforcement Learning
Ahmadreza Moradipari, Mohammad Pedramfar, Modjtaba Shokrian Zini, Vaneet Aggarwal
Reinforcement Learning Thompson Sampling Finite Mixture

June 5, 2023

COMET: Learning Cardinality Constrained Mixture of Experts with Trees and Local Search
Shibal Ibrahim, Wenyu Chen, Hussein Hazimeh, Natalia Ponomareva, Zhe Zhao, Rahul Mazumder
Expert Knowledge Tree Specie Local Search Chasing COMET Sparse Expert Finite Mixture Sparse MoEs Sparse Gate

May 15, 2023

FiMReSt: Finite Mixture of Multivariate Regulated Skew-t Kernels -- A Flexible Probabilistic Model for Multi-Clustered Data with Asymmetrically-Scattered Non-Gaussian Kernels
Sarmad Mehrdad, S. Farokh Atashzar
Mixture Model Finite Mixture Asymmetric Kernel Skew T Copula

December 1, 2022

Implicit Mixture of Interpretable Experts for Global and Local Interpretability
Nathan Elazar, Kerry Taylor
World Event Interpretable Image Expert Annotated Global Interpretability Local Interpretability Finite Mixture Intelligent Routing

November 15, 2022

The Association Between SOC and Land Prices Considering Spatial Heterogeneity Based on Finite Mixture Modeling
Woo Seok Kang, Eunchan Kim, Wookjae Heo
Association Capability Real Estate Spatial Feature Finite Mixture Spatial Heterogeneity Spatial Clustering MM Soc

October 27, 2022

Simultaneous off-the-grid learning of mixtures issued from a continuous dictionary
Cristina Butucea, Jean-François Delmas, Anne Dutfoy, Clément Hardy
Mixture Component RSD Difference of Gaussian Group Lasso Finite Mixture Norm Penalty

September 13, 2022

A Non-Parametric Bootstrap for Spectral Clustering
Liam Welsh, Phillip Shreeves
Spectral Clustering Parametric Bootstrap Finite Mixture

July 22, 2022

Generalized Identifiability Bounds for Mixture Models with Grouped Samples
Robert A. Vandermeulen, René Saitenmacher
Mixture Model Novel Identifiability Test Partial Identifiability Finite Mixture Independent Sampling Mixture Markov Model Multinomial Mixture

June 29, 2022

Off-the-grid learning of sparse mixtures from a continuous dictionary
Cristina Butucea, Jean-François Delmas, Anne Dutfoy, Clément Hardy
Many Sparse Nonlinear Model LASSO Regression Finite Mixture Offline Model Based Optimization

May 27, 2022

Finite mixture of skewed sub-Gaussian stable distributions
Mahdi Teimouri
Model Based Clustering Finite Mixture Skewed Non IID

March 28, 2022

Tight Bounds on the Hardness of Learning Simple Nonparametric Mixtures
Bryon Aragam, Wai Ming Tai
Sample Complexity Hardness Result Tight Bound Multiple Distribution Finite Mixture