Research map / Bandits and online learning / Online convex optimization and games
Near-Optimal Policies for Dynamic Multinomial Logit Assortment Selection Models
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 Hoeffding confidence intervals with LIL intervals and adaptive confidence level | trisection algorithm · synthetic MNL, all (N,T) | regret: 7.44 -> 4.74 (N=1000,T=500 mean) | Helped |
| trisection (item-independent) instead of UCB on large item sets | uncapacitated MNL assortment · synthetic, N=1000, T=1000 | mean regret: 160.8 -> 9.77 | Helped |
| trisection versus Thompson sampling at small N | TRISEC / LIL-TRISEC · synthetic, N=100 | mean regret: 1.28 (Thompson) vs 7.68 (TRISEC) | Hurt |
| LIL-trisection versus golden-ratio search | LIL-TRISEC · synthetic, N=100, T=1000 | mean regret: 139.9 -> 5.36 | Helped |
Closest papers by meaning
- Nearly Minimax Optimal Regret for Multinomial Logistic Bandit (NeurIPS 2024 · similarity 0.91)
- 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)
- Online Learning of Delayed Choices (NeurIPS 2024 · similarity 0.88)
- Dynamic Assortment Selection and Pricing with Censored Preference Feedback (ICLR 2025 · similarity 0.88)
- Stochastic Matching Bandits with Rare Optimization Updates (NeurIPS 2026 · 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.