Research map / Bandits and online learning / Online convex optimization and games
Low-Rank Bandit Methods for High-Dimensional Dynamic Pricing
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 |
|---|---|---|---|
| Exploit the low-rank demand structure with OPOK or OPOL instead of GDG | Dynamic pricing with many products and intrinsic rank below the product count · Synthetic stationary demand | cumulative regret | Helped |
| Use OPOK or OPOL when the action dimension has no low-rank reduction to exploit | Dynamic pricing with N = d · Synthetic stationary demand | cumulative regret | No clear effect |
| Estimate the latent product subspace online with OPOL rather than using known features with OPOK | Dynamic pricing under noisy demand · Synthetic stationary demand | cumulative regret | Helped |
| Use low-rank OPOK or OPOL instead of GDG or explore-then-exploit | Dynamic pricing with many products · Synthetic demand with structural shocks | cumulative regret | Helped |
| Use low-rank OPOK or OPOL instead of GDG or explore-then-exploit | Dynamic pricing with many products · Synthetic drifting demand | cumulative regret | Helped |
| Apply OPOL with a low assumed rank despite violating the low-rank demand assumption | High-dimensional dynamic pricing · Misspecified full-rank or log-linear demand | cumulative regret | Helped |
Closest papers by meaning
- Learning to price with resource constraints: from full information to machine-learned prices (NeurIPS 2025 · similarity 0.88)
- Non-stochastic Budgeted Online Pricing with Semi-Bandit Feedback (AAAI 2025 · similarity 0.88)
- Transfer Faster, Price Smarter: Minimax Dynamic Pricing under Cross-Market Preference Shift (NeurIPS 2025 · similarity 0.87)
- Improved learning rates in multi-unit uniform price auctions (NeurIPS 2024 · similarity 0.86)
- Learning to Price Homogeneous Data (NeurIPS 2024 · similarity 0.86)
- Toward Optimal Regret in Robust Pricing: Decoupling Corruption and Time (NeurIPS 2026 · 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.