DeepAI AI Chat
Log In Sign Up

Convergence Rates of Latent Topic Models Under Relaxed Identifiability Conditions

by   Yining Wang, et al.

In this paper we study the frequentist convergence rate for the Latent Dirichlet Allocation (Blei et al., 2003) topic models. We show that the maximum likelihood estimator converges to one of the finitely many equivalent parameters in Wasserstein's distance metric at a rate of n^-1/4 without assuming separability or non-degeneracy of the underlying topics and/or the existence of more than three words per document, thus generalizing the previous works of Anandkumar et al. (2012, 2014) from an information-theoretical perspective. We also show that the n^-1/4 convergence rate is optimal in the worst case.


page 1

page 2

page 3

page 4


An Explicit Rate Bound for the Over-Relaxed ADMM

The framework of Integral Quadratic Constraints of Lessard et al. (2014)...

Minimum Volume Topic Modeling

We propose a new topic modeling procedure that takes advantage of the fa...

Uncoupled and Convergent Learning in Two-Player Zero-Sum Markov Games

We revisit the problem of learning in two-player zero-sum Markov games, ...

Learning Topic Models: Identifiability and Finite-Sample Analysis

Topic models provide a useful text-mining tool for learning, extracting ...

Convergence Rates for Mixture-of-Experts

In mixtures-of-experts (ME) model, where a number of submodels (experts)...

Guaranteed inference in topic models

One of the core problems in statistical models is the estimation of a po...

Determining Research Priorities for Astronomy Using Machine Learning

We summarize the first exploratory investigation into whether Machine Le...