High Dimensional EM Algorithm: Statistical Optimization and Asymptotic Normality

Authors: Zhaoran Wang, Quanquan Gu, Yang Ning, Han Liu

NeurIPS 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We provide a general theory of the expectation-maximization (EM) algorithm for inferring high dimensional latent variable models. ... For a broad family of statistical models, our framework establishes the first computationally feasible approach for optimal estimation and asymptotic inference in high dimensions.
Researcher Affiliation Academia Zhaoran Wang Princeton University Quanquan Gu University of Virginia Yang Ning Princeton University Han Liu Princeton University
Pseudocode Yes Algorithm 1 High Dimensional EM Algorithm... Algorithm 2 Maximization Implementation of the M-step... Algorithm 3 Gradient Ascent Implementation of the M-step
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets No The paper discusses theoretical applications to 'Gaussian Mixture Model' and 'Mixture of Regression Model' but does not use or provide information for a specific training dataset.
Dataset Splits No The paper is theoretical and does not describe experimental validation or dataset splits.
Hardware Specification No The paper describes theoretical work and does not provide specific hardware details used for running experiments.
Software Dependencies No The paper describes theoretical work and does not provide specific ancillary software details with version numbers.
Experiment Setup No The paper describes theoretical work and does not provide specific experimental setup details.