ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2405.17806
22
1

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

28 May 2024
Z. T. Ke
Jingming Wang
ArXivPDFHTML
Abstract

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 nnn documents, a vocabulary of size ppp, and document lengths at the order NNN. When N≥c⋅pN\geq c\cdot pN≥c⋅p, referred to as the long-document case, the optimal rate is established in the literature at p/(Nn)\sqrt{p/(Nn)}p/(Nn)​. However, when N=o(p)N=o(p)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 p/(Nn)\sqrt{p/(Nn)}p/(Nn)​ in the short-document case.

View on arXiv
Comments on this paper