Entry-Wise Eigenvector Analysis and Improved Rates for Topic Modeling on Short Documents

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ke, Zheng Tracy, Wang, Jingming
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914814319656960
author Ke, Zheng Tracy
Wang, Jingming
author_facet Ke, Zheng Tracy
Wang, Jingming
contents Topic modeling is a widely utilized tool in text analysis. We investigate the optimal rate for estimating a topic model. Specifically, we consider a scenario with $n$ documents, a vocabulary of size $p$, and document lengths at the order $N$. When $N\geq c\cdot p$, referred to as the long-document case, the optimal rate is established in the literature at $\sqrt{p/(Nn)}$. However, when $N=o(p)$, referred to as the short-document case, the optimal rate remains unknown. In this paper, we first provide new entry-wise large-deviation bounds for the empirical singular vectors of a topic model. We then apply these bounds to improve the error rate of a spectral algorithm, Topic-SCORE. Finally, by comparing the improved error rate with the minimax lower bound, we conclude that the optimal rate is still $\sqrt{p/(Nn)}$ in the short-document case.
format Preprint
id arxiv_https___arxiv_org_abs_2405_17806
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Entry-Wise Eigenvector Analysis and Improved Rates for Topic Modeling on Short Documents
Ke, Zheng Tracy
Wang, Jingming
Statistics Theory
62H12
Topic modeling is a widely utilized tool in text analysis. We investigate the optimal rate for estimating a topic model. Specifically, we consider a scenario with $n$ documents, a vocabulary of size $p$, and document lengths at the order $N$. When $N\geq c\cdot p$, referred to as the long-document case, the optimal rate is established in the literature at $\sqrt{p/(Nn)}$. However, when $N=o(p)$, referred to as the short-document case, the optimal rate remains unknown. In this paper, we first provide new entry-wise large-deviation bounds for the empirical singular vectors of a topic model. We then apply these bounds to improve the error rate of a spectral algorithm, Topic-SCORE. Finally, by comparing the improved error rate with the minimax lower bound, we conclude that the optimal rate is still $\sqrt{p/(Nn)}$ in the short-document case.
title Entry-Wise Eigenvector Analysis and Improved Rates for Topic Modeling on Short Documents
topic Statistics Theory
62H12
url https://arxiv.org/abs/2405.17806