Convergence rates of latent topic models under relaxed identifiability conditions (Q1711601)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 7003257
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Convergence rates of latent topic models under relaxed identifiability conditions |
scientific article; zbMATH DE number 7003257 |
Statements
Convergence rates of latent topic models under relaxed identifiability conditions (English)
0 references
18 January 2019
0 references
The paper under review explores the convergence rate for the latent Dirichlet allocation topic models introduced by \textit{D. M. Blei} et al. [J. Mach. Learn. Res. 3, No. 4--5, 993--1022 (2003; Zbl 1112.68379)]. The estimation error between the underlying true model and an estimator is evaluated by the Wasserstein's distance. The convergence rate of the maximum likelihood estimator is obtained in the general case, thus generalizing the previous works of \textit{A. Anandkumar} et al. [Algorithmica 72, No. 1, 193--214 (2015; Zbl 1311.68130); J. Mach. Learn. Res. 15, 2239--2312 (2014; Zbl 1318.68136)].
0 references
latent Dirichlet allocation
0 references
topic models
0 references
maximum likelihood
0 references
rates of convergence
0 references
0 references
0 references
0 references
0.7861401438713074
0 references
0.7381390333175659
0 references
0.7262133955955505
0 references
0.7230991125106812
0 references
0.7203769683837891
0 references
