Research map / Learning theory and algorithms / Matrix and tensor methods
Estimation of Markov Chain via Rank-Constrained Likelihood
Xudong Li, Mengdi Wang, Anru Zhang
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 rank-constrained maximum likelihood instead of plain maximum likelihood | Low-rank Markov-chain estimation · Simulated Markov chain (p=500, r=10) | ηF | Improved |
| Use rank-constrained maximum likelihood instead of plain maximum likelihood | Low-rank Markov-chain estimation · Simulated Markov chain (p=500, r=10) | ηU | Improved |
| Use rank-constrained maximum likelihood instead of plain maximum likelihood | Low-rank Markov-chain estimation · Simulated Markov chain (p=500, r=10) | ηV | Improved |
| Use rank-constrained maximum likelihood instead of truncated SVD | Low-rank Markov-chain estimation · Simulated Markov chain (p=500, r=10) | ηF | Improved |
| Use rank-constrained maximum likelihood instead of truncated SVD | Low-rank Markov-chain estimation · Simulated Markov chain (p=500, r=10) | ηU | Improved |
| Use rank-constrained maximum likelihood instead of truncated SVD | Low-rank Markov-chain estimation · Simulated Markov chain (p=500, r=10) | ηV | Improved |
| Use rank-constrained maximum likelihood instead of nuclear-norm penalized estimation | Low-rank Markov-chain estimation · Simulated Markov chain (p=500, r=10) | ηF | Improved |
| Use rank-constrained maximum likelihood instead of nuclear-norm penalized estimation | Low-rank Markov-chain estimation · Simulated Markov chain (p=500, r=10) | ηU | Improved |
| Use rank-constrained maximum likelihood instead of nuclear-norm penalized estimation | Low-rank Markov-chain estimation · Simulated Markov chain (p=500, r=10) | ηV | Improved |
Closest papers by meaning
- On Learning Markov Chains (NeurIPS 2018 · similarity 0.88)
- Learning from A Single Markovian Trajectory: Optimality and Variance Reduction (NeurIPS 2025 · similarity 0.87)
- Just Wing It: Near-Optimal Estimation of Missing Mass in a Markovian Sequence (JMLR 2024 · similarity 0.87)
- Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes (NeurIPS 2024 · similarity 0.85)
- Multi-Marginal Couplings for Metropolis--Hastings (NeurIPS 2026 · similarity 0.85)
- Distances for Markov chains from sample streams (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.
