Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Robust Contextual Pricing
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Gives a regret bound O(C d log log T) for contextual pricing with C corrupted rounds via a black-box reduction to the uncorrupted algorithm.
Problem
Contextual pricing (online learning of a buyer's valuation from context) when some rounds are adversarially corrupted, where regret must degrade gracefully with the number of corruptions.
Approach
A reduction that treats the uncorrupted contextual pricing algorithm as a black box, rather than modifying its internals as in prior corrupted-setting work, yielding a regret of O(C d log log T) that improves on the earlier O(d^3 C log^2 T) bound and gives a conceptually simpler algorithm.
Key results
- Regret bound O(C d log log T) for contextual pricing with C corrupted rounds, improving on the previous O(d^3 C log^2 T) of Krishnamurthy et al.
Experimental setup
Metrics: regret
Baselines: Krishnamurthy et al. corrupted contextual pricing algorithm
Builds on: Krishnamurthy et al. contextual pricing with corruptions
Closest papers by meaning
- Toward Optimal Regret in Robust Pricing: Decoupling Corruption and Time (NeurIPS 2026 · similarity 0.91)
- Optimal Contextual Pricing under Agnostic Non-Lipschitz Demand (NeurIPS 2026 · similarity 0.91)
- Improved Algorithms for Contextual Dynamic Pricing (NeurIPS 2024 · similarity 0.91)
- Contextual Online Pricing with (Biased) Offline Data (NeurIPS 2025 · similarity 0.89)
- Contextual Dynamic Pricing with Heterogeneous Buyers (NeurIPS 2025 · similarity 0.88)
- Learning to price with resource constraints: from full information to machine-learned prices (NeurIPS 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.