Research map / Learning theory and algorithms / Sample complexity
Provable Algorithms for Inference in Topic Models
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Restrict MLE to the known support R of x* (r-sparse) and optimize log-likelihood over those coordinates only | MLE for topic proportions in topic models · theoretical analysis (Theorem, n >= c kappa^2 r^2 log k / tau^2) | l1 error ||x_mle - x*||_1 | Helped |
| Use the linear inverse (recovered x) with smoothing of log(Ax) and an l1-condition-number argument to bound the likelihood of the linear estimator | linear inverse estimator for topic proportions · theoretical analysis (claim with O~(r^2/(delta^2 eps^2)) samples) | expected negative log-likelihood gap to optimum | No clear effect |
Closest papers by meaning
- An Instability in Variational Inference for Topic Models (ICML 2019 · similarity 0.89)
- Diagnosing and Improving Topic Models by Analyzing Posterior Variability (AAAI 2018 · similarity 0.89)
- Discovering Discrete Latent Topics with Neural Variational Inference (ICML 2017 · similarity 0.88)
- E-LDA: Toward Interpretable LDA Topic Models with Strong Guarantees in Logarithmic Parallel Time (ICML 2025 · similarity 0.87)
- Autoencoding Variational Inference For Topic Models (ICLR 2017 · similarity 0.87)
- Provable unlearning in topic modeling and downstream tasks (ICLR 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.