Abstract
We show a regret minimization algorithm for setting the reserve price in a sequence of second-price auctions, under the assumption that all bids are independently drawn from the same unknown and arbitrary distribution. Our algorithm is computationally efficient, and achieves a regret of Q{script}(√T) in a sequence of T auctions. This holds even when the number of bidders is stochastic with a known distribution.
Original language | English |
---|---|
Article number | 6939698 |
Pages (from-to) | 549-564 |
Number of pages | 16 |
Journal | IEEE Transactions on Information Theory |
Volume | 61 |
Issue number | 1 |
DOIs | |
State | Published - 1 Jan 2015 |
Keywords
- Prediction theory
- semi-supervised learning
- sequential analysis
- statistical learning
All Science Journal Classification (ASJC) codes
- Information Systems
- Computer Science Applications
- Library and Information Sciences