Assigning topics to documents by successive projections

DOI10.1214/23-aos2316arXiv2107.03684OpenAlexW3179642146MaRDI QIDQ6183768

Olga Klopp, Alexandre B. Tsybakov, Suzanne Sigalla, Maxim E. Panov

Publication date: 4 January 2024

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2107.03684

zbMATH Keywords

adaptive estimationminimax rate of convergencenonnegative matrix factorizationtopic modellatent variable model

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Combinatorial probability (60C05)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Robustness analysis of preconditioned successive projection algorithm for general form of separable NMF problem
• A correlated topic model of science
• Likelihood estimation of sparse topic distributions in topic models and its applications to Wasserstein document distance calculations
• A fast algorithm with minimax optimal guarantees for topic models with an unknown number of topics
• Consistency of spectral clustering in stochastic block models
• A spectral algorithm for latent Dirichlet allocation
• Tensor decompositions for learning latent variable models
• Learning Arbitrary Statistical Mixtures of Discrete Distributions
• 10.1162/jmlr.2003.3.4-5.993
• Spectral analysis of data
• Semidefinite Programming Based Preconditioning for More Robust Near-Separable Nonnegative Matrix Factorization
• Learning the parts of objects by non-negative matrix factorization
• An Introduction to Matrix Concentration Inequalities
• Estimating Mixed Memberships With Sharp Eigenvector Deviations