Research map / Learning theory and algorithms / Matrix and tensor methods
Optimal Estimation of Sparse Topic Models
Xin Bing, Florentina Bunea, Marten Wegkamp
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| use TOP anchor selection (unknown K) instead of AWR with given K inside the sparse estimator | STM · synthetic, sparsity sweep | estimation error | Improved |
| add the sparsity-adaptive thresholding step (STM) on top of TOP | TOP · synthetic, sparsity sweep | estimation error | Improved |
| add the sparsity-adaptive step (STM) on top of AWR | AWR · NYT semi-synthetic with anchor words | estimation error | Improved |
| increase anchor words per topic from 1 to 5 (ablation) | TOP and STM-TOP · NIPs and NYT semi-synthetic | estimation error | Improved |
| use STM-AWR instead of AWR when topics are correlated | AWR · NIPs, correlated topics | estimation error | Improved |
| use LDA instead of the moment-based algorithms | LDA · NIPs semi-synthetic | running time (seconds): 1918.7 -> 9130.6 | Hurt |
| use STM-TOP instead of TOP | TOP · NIPs semi-synthetic, n=2000 | running time (seconds): 35.2 -> 614.3 | Hurt |
Closest papers by meaning
- Sparse Topic Modeling via Spectral Decomposition and Thresholding (JMLR 2026 · similarity 0.92)
- Probabilistic Non-Negative Matrix Factorization and Its Robust Extensions for Topic Modeling (AAAI 2017 · similarity 0.89)
- Provable Algorithms for Inference in Topic Models (ICML 2016 · similarity 0.88)
- Pólya Urn Latent Dirichlet Allocation: A Doubly Sparse Massively Parallel Sampler (TPAMI 2018 · similarity 0.86)
- A Statistical Approach for Optimal Topic Model Identification (JMLR 2022 · similarity 0.86)
- A Reduction for Efficient LDA Topic Reconstruction (NeurIPS 2018 · 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.
