Research map / Learning theory and algorithms / Optimal transport
Optimal Transport for Stationary Markov Chains via Policy Iteration
Kevin O'Connor, Kevin McGoff, Andrew B. Nobel
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 |
|---|---|---|---|
| replace exact policy iteration with entropy-regularized approximate version | ExactOTC · Simulation, random chains d=100, xi=100 | total runtime: roughly 80% | Improved |
| weaken regularization by increasing xi (75, 100, 200) (ablation) | EntropicOTC · Simulation, random chains d=10 to 100 | approximation error | Improved |
| replace 1-step transition coupling with infinite-horizon OTC | 1-step OTC · Appendix example | expected cost: 5/3 -> 1 | Improved |
| use EntropicOTC instead of ExactOTC for pairwise piece costs | ExactOTC · Music HMM pairs (36 pieces) | pairwise OTC cost: 8 x 10^-3 average difference | No clear effect |
Closest papers by meaning
- Bisimulation Metrics are Optimal Transport Distances, and Can be Computed Efficiently (NeurIPS 2024 · similarity 0.89)
- Distances for Markov chains from sample streams (NeurIPS 2025 · similarity 0.85)
- Low-Rank Optimal Transport through Factor Relaxation with Latent Coupling (NeurIPS 2024 · similarity 0.85)
- Persistent-Transient Policy Evaluation for Markov Chains via Minimal Peripheral Quotients (NeurIPS 2026 · similarity 0.85)
- Multi-Marginal Couplings for Metropolis--Hastings (NeurIPS 2026 · similarity 0.85)
- The Collusion of Memory and Nonlinearity in Stochastic Approximation With Constant Stepsize (NeurIPS 2024 · similarity 0.84)
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.
