Research map / Bandits and online learning / Online convex optimization and games
PASTA: Pessimistic Assortment Optimization
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 |
|---|---|---|---|
| Use pessimistic optimization instead of plug-in estimate-then-optimize | Offline assortment optimization · Synthetic data, varying sample size n; N=40, K=8, d=16, p=0.9 | average regret: less than 25% of that of the baseline method | Helped |
| Use pessimistic optimization instead of plug-in estimate-then-optimize | Offline assortment optimization · Synthetic data, varying sample size n; N=60, K=15 | average regret | Helped |
| Use pessimistic optimization instead of plug-in estimate-then-optimize | Offline assortment optimization · Synthetic data, varying probability p of sampling the optimal assortment; N=40 and N=60 | average regret | Helped |
| Use pessimistic optimization instead of plug-in estimate-then-optimize | Offline assortment optimization · Synthetic data, varying feature dimension d; N=20, K=5, p=0.9, n=150 | average regret | Helped |
Closest papers by meaning
- Tractable Multinomial Logit Contextual Bandits with Non-Linear Utilities (NeurIPS 2025 · similarity 0.85)
- Online Learning of Delayed Choices (NeurIPS 2024 · similarity 0.84)
- Contextual Multinomial Logit Bandits with General Value Functions (NeurIPS 2024 · similarity 0.84)
- Dynamic Assortment Selection and Pricing with Censored Preference Feedback (ICLR 2025 · similarity 0.84)
- Nearly Minimax Optimal Regret for Multinomial Logistic Bandit (NeurIPS 2024 · similarity 0.83)
- Regret minimization in Linear Bandits with offline data via extended D-optimal exploration. (NeurIPS 2026 · similarity 0.82)
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.