Skip to content
conftrace_
2018 JMLR JMLR 2018

Maximum Likelihood Estimation for Mixtures of Spherical Gaussians is NP-hard

Abstract

This paper presents NP-hardness and hardness of approximation results for maximum likelihood estimation of mixtures of spherical Gaussians. [abs] [ pdf ][ bib ] © JMLR 2018. (edit, beta)

🌉 Interdisciplinary Bridge - Artificial Intelligence and Mathematics & Optimization
🐣 Hot Topic Early Bird - maximum likelihood estimation

Authors

Christopher Tosh, Sanjoy Dasgupta

Topics

Machine Learning > Optimization & Theory > Statistical Learning Machine Learning > Optimization & Theory > Theory Mathematics & Optimization > Mathematics > Probability

Keywords

parameter estimation maximum likelihood estimation mixture of gaussian spherical gaussian
Download PDF

More from JMLR 2018

All JMLR 2018 papers →
Convergence Analysis of Distributed Inference with Vector-Valued Gaussian Belief Propagation
auDeep: Unsupervised Learning of Representations from Audio with Deep Recurrent Neural Networks
On the Stability of Feature Selection Algorithms
The DFS Fused Lasso: Linear-Time Denoising over General Graphs
Community Detection and Stochastic Block Models: Recent Developments
On b-bit Min-wise Hashing for Large-scale Regression and Classification with Sparse Data