Abstract: Designing an auction that maximizes expected revenue is a major open problem in economics. Despite significant effort, only the single-item case is fully understood. We ask whether the tools of deep learning can be used to make progress. We show that multi-layer neural networks can learn essentially optimal auction designs for the few problems that have been solved analytically, and can be used to design auctions for poorly understood problems, including settings with multiple items and budget constraints. I will also overview applications to other problems of optimal economic design, and discuss the broader implications of this work. Joint work with Paul Duetting (London School of Economics), Zhe Feng (Harvard University), Noah Golowich (Harvard University), Harikrishna Narasimhan (Harvard -> Google), and Sai Srivatsa (Harvard University). Working paper: https://arxiv.org/abs/1706.03459
A buffet lunch will be available at 11:45 a.m. The talk will begin at 12:00 p.m.
David is the George F. Colony Professor of Computer Science in the Paulson School of Engineering and Applied Sciences (SEAS) and Co-Director of the Harvard Data Science Initiative.