Research map / Optimization / Nonconvex and smooth optimization
Modified Frank Wolfe in Probability Space
Carson Kent, Jiajin Li, Jose Blanchet, Peter Glynn
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 robust MCE IRL (opponent strength 1-alpha) on top of standard MCE IRL | MCE IRL · GridWorld and ObjectWorld under dynamics mismatch | value of learned policy in learner MDP | Improved |
| use robust MCE IRL when expert noise is low (little mismatch) | Robust MCE IRL · GridWorld and ObjectWorld, low expert noise | value of learned policy in learner MDP | Hurt |
| underestimate the opponent strength 1-alpha so the expert dynamics lie outside the uncertainty set (ablation) | Robust MCE IRL · GridWorld and ObjectWorld | value of learned policy in learner MDP | Hurt |
| overestimate the opponent strength 1-alpha (ablation) | Robust MCE IRL · GridWorld and ObjectWorld | value of learned policy in learner MDP | Hurt |
| set 1-alpha near half the distance between learner dynamics and a rough estimate of expert dynamics (ablation) | Robust MCE IRL · GridWorld and ObjectWorld | value of learned policy in learner MDP | Improved |
| increase dynamics mismatch (expert noise) for standard MCE IRL | Standard MCE IRL · GridWorld and ObjectWorld | value of learned policy in learner MDP | Hurt |
| add robust variant to Relative Entropy IRL in continuous state-action space | RE IRL · GaussianGrid | value of learned policy in learner MDP | Improved |
| add robust training to MCE IRL with low-dimensional feature mapping | MCE IRL · low-dimensional feature GridWorld (appendix) | value of learned policy in learner MDP | Improved |
| choose alpha = 1 - d_dyn/2 in the constructive three-state example | Robust MCE IRL · constructive example MDP | performance gap to no-mismatch MCE IRL | Improved |
Closest papers by meaning
- Sarah Frank-Wolfe: Methods for Constrained Optimization with Best Rates and Practical Features (ICML 2024 · similarity 0.89)
- Stochastic Frank-Wolfe for Constrained Finite-Sum Minimization (ICML 2020 · similarity 0.89)
- Efficient Quadratic Corrections for Frank-Wolfe Algorithms (NeurIPS 2025 · similarity 0.86)
- Mirror and Preconditioned Gradient Descent in Wasserstein Space (NeurIPS 2024 · similarity 0.86)
- Frank-Wolfe Beyond 1/t Convergence (NeurIPS 2026 · similarity 0.86)
- Hessian-guided Perturbed Wasserstein Gradient Flows for Escaping Saddle Points (NeurIPS 2025 · similarity 0.86)
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.
