Research map / Learning theory and algorithms / Sample complexity
Robustifying Algorithms of Learning Latent Trees with Vector Variables
Fengzhuo Zhang, Vincent Tan
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 |
|---|---|---|---|
| Add Chow-Liu initialization before Recursive Grouping | RRG, yielding RCLRG · HMM | clean-sample complexity: O\big((\frac{9}{2})^{\mathrm{Diam}(\mathbb{T})}\big) to O\big(\log \mathrm{Diam}(\mathbb{T})\big) | Improved |
| Use truncated inner products to estimate information distances | RRG, RCLRG, RNJ, and RSNJ · Latent Gaussian trees with arbitrary corruptions | corruption tolerance: n_{1}=O\big(\frac{\sqrt{n_{2}}}{\log n_{2}}\big) | Improved |
| Robustify the algorithms using truncated inner products | RRG, RCLRG, RNJ, and RSNJ · HMM simulations with uniform, constant-magnitude, and HMM corruptions | Robinson-Foulds distance | Improved |
| Use Chow-Liu initialization to shorten error propagation from L_R to L_C | RCLRG · Latent tree structure learning | clean-sample complexity: L_{\mathrm{C}}\ll L_{\mathrm{R}} | Improved |
Closest papers by meaning
- SGA: A Robust Algorithm for Partial Recovery of Tree-Structured Graphical Models with Noisy Samples (ICML 2021 · similarity 0.89)
- Robust Learning of Fixed-Structure Bayesian Networks in Nearly-Linear Time (ICLR 2021 · similarity 0.86)
- Learning Mixed Latent Tree Models (JMLR 2020 · similarity 0.86)
- Algebraic tests of general Gaussian latent tree models (NeurIPS 2018 · similarity 0.86)
- TreeVI: Reparameterizable Tree-structured Variational Inference for Instance-level Correlation Capturing (NeurIPS 2024 · similarity 0.85)
- Distribution Learning Meets Graph Structure Sampling (NeurIPS 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.
