Research map / Bandits and online learning / Online convex optimization and games
Optimal Design for Multinomial Logit Model with Applications to Best Assortment Identification
Joongkyu Lee, Min-hwan Oh
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 brute-force LMO enumeration with polynomial-time Schur-complement lifted LMO | BSI-MNL · LMO runtime, N=100, K=5 | avg LMO runtime (s): 9048.44 -> 0.17 | Improved |
| replace brute-force LMO enumeration with MILP reformulation | BSI-MNL · LMO runtime, N=200, K=4 | avg LMO runtime (s): 7154.85 -> 271.88 | Improved |
| use MILP instead of brute-force LMO on small instances | BSI-MNL · LMO runtime, N=30, K=3 | avg LMO runtime (s): 0.38 -> 2.06 | Hurt |
| use MILP or lifted LMO in place of exact oracle | BSI-MNL · stopping time, N from 10 to 50, K from 2 to 5 | stopping time | No clear effect |
Closest papers by meaning
- Nearly Minimax Optimal Regret for Multinomial Logistic Bandit (NeurIPS 2024 · similarity 0.90)
- Tractable Multinomial Logit Contextual Bandits with Non-Linear Utilities (NeurIPS 2025 · similarity 0.90)
- Contextual Multinomial Logit Bandits with General Value Functions (NeurIPS 2024 · similarity 0.89)
- Stochastic Matching Bandits with Rare Optimization Updates (NeurIPS 2026 · similarity 0.88)
- Improved Online Confidence Bounds for Multinomial Logistic Bandits (ICML 2025 · similarity 0.87)
- Optimal and Practical Batched Linear Bandit Algorithm (ICML 2025 · similarity 0.87)
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.
