Research map / Bandits and online learning / Online convex optimization and games
Double Auctions with Two-sided Bandit Feedback
Soumya Basu, Abishek Sankararaman
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 |
|---|---|---|---|
| use UCB for buyers and LCB for sellers in the average-mechanism double auction | buyers and sellers with unknown valuations · synthetic 8x8 system, K*=5 | number of matches K(t): converges to 5 | Improved |
| use UCB for buyers and LCB for sellers | double auction · synthetic 8x8 system | price difference p(t)-p*: converges to 0 | Improved |
| use UCB for buyers and LCB for sellers | double auction · synthetic, T=50k, 100 paths | social regret | Improved |
| use optimism on both sides (OFUL) in two-sided uncertainty | double auction learners · theory | information flow | Hurt |
Closest papers by meaning
- Beyond $log^2(T)$ regret for decentralized bandits in matching markets (ICML 2021 · similarity 0.91)
- Improved Analysis for Bandit Learning in Matching Markets (NeurIPS 2024 · similarity 0.90)
- Comparing Uniform Price and Discriminatory Multi-Unit Auctions through Regret Minimization (NeurIPS 2025 · similarity 0.89)
- Improved Bandits in Many-to-One Matching Markets with Incentive Compatibility (AAAI 2024 · similarity 0.89)
- Fair Online Bilateral Trade (NeurIPS 2024 · similarity 0.88)
- Competing Bandits in Matching Markets via Super Stability (ICML 2025 · similarity 0.88)
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.
