Mixture models, robustness, and sum of squares proofs

DOI10.1145/3188745.3188748zbMath1428.68240arXiv1711.07454OpenAlexW2962820675MaRDI QIDQ5230359

Samuel B. Hopkins, Jerry Li

Publication date: 22 August 2019

Published in: Proceedings of the 50th Annual ACM SIGACT Symposium on Theory of Computing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1711.07454

zbMATH Keywords

semidefinite programmingclusteringunsupervised learningrobust statisticsmixture modelshigh-dimensional statisticsmixture of Gaussianssum-of-squares method

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Robustness and adaptive procedures (parametric inference) (62F35) Learning and adaptive systems in artificial intelligence (68T05)

Related Items (15)

GAT–GMM: Generative Adversarial Training for Gaussian Mixture Models ⋮ Optimal estimation of high-dimensional Gaussian location mixtures ⋮ A faster interior-point method for sum-of-squares optimization ⋮ Mean estimation with sub-Gaussian rates in polynomial time ⋮ Unnamed Item ⋮ Optimal estimation of Gaussian mixtures via denoised method of moments ⋮ Robust Estimators in High-Dimensions Without the Computational Intractability ⋮ Unnamed Item ⋮ Sum-of-squares lower bounds for densest \(k\)-subgraph ⋮ Learning polynomial transformations via generalized tensor decompositions ⋮ Algorithms approaching the threshold for semi-random planted clique ⋮ Partial recovery bounds for clustering with the relaxed \(K\)-means ⋮ Mean estimation and regression under heavy-tailed distributions: A survey ⋮ Hidden Integrality and Semirandom Robustness of SDP Relaxation for Sub-Gaussian Mixture Model ⋮ Graph Powering and Spectral Robustness

This page was built for publication: Mixture models, robustness, and sum of squares proofs