We will have three keynote talks:

Nicolas Stier (Facebook): Pacing Mechanisms For Ad Auctions

Budgets play a significant role in real-world sequential auction markets such as those implemented by Internet companies. To maximize the value provided to auction participants, spending is smoothed across auctions so budgets are used for the best opportunities. Motivated by pacing mechanisms used in practice by online ad auction platforms, we discus smoothing procedures that ensure that campaign daily budgets are consistent with maximum bids. Reinterpreting this process as a game between bidders, we introduce the notion of pacing equilibrium, and study properties such as existence, uniqueness, complexity and efficiency, both for the case of second and first price auctions. In addition, we connect these equilibria to more general notions of market equilibria, and study how compact representations of a market lead to more efficient approaches to compute approximate equilibria.

Bio: I’m a Co-Director of Facebook Core Data Science. Our work leverages innovative research to drive impact to the products, infrastructure and processes at Facebook. We draw from a rich and diverse set of backgrounds including Operations, Statistics, Economics, Mechanism Design, Machine Learning, Experimentation, Algorithms, and Computational Social Science (in no particular order). Between 2014 and 2017, I supported the Business and Operations team, which is one the areas of focus of Core Data Science. Prior to Facebook, I was an Associate Professor at the Decision, Risk and Operations Division of Columbia Business School and at the Business School of Universidad Torcuato Di Tella. I received a Ph.D. degree from the Operations Research Center of the Massachusetts Institute of Technology.


Itai Ashlagi (Stanford University): Clearing matching markets efficiently: informative signals and match recommendations

We will study congestion in two-sided matching markets with private preferences. We measure congestion by the number of bits of information that agents must (i) learn about their own preferences, and (ii) communicate with others before obtaining their final match. Previous results by Segal (2007) and Gonczarowski et al. (2015) suggest that a high level of congestion is inevitable under arbitrary preferences before the market can clear with a stable matching. We show that when the unobservable component of agent preferences satisfies certain natural assumptions, it is possible to recommend potential matches and encourage informative signals such that the market reaches a stable matching with a low level of congestion. This is desirable because the communication overhead is minimized while agents have negligible incentives to leave the marketplace or to look beyond the set of recommended partners. The main idea is to only recommend partners with whom the agent has a non-negligible chance of both liking and being liked by. The recommendations are based both on the observable component of preferences, and on the signals sent by agents on the other side that indicate interest.

Bio: Itai Ashlagi is an Associate Professor of Management Science and Engineering at Stanford University. He is interested in mechanism and market design, matching, and game theory and have contributed to the design of several kidney exchange platforms. He is the recipient of the NSF CAREER award and a Franz Edelman Laureate.

David C. Parkes (Harvard University): Optimal Economic Design through Deep Learning

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).

Bio: David Parkes is the George F. Colony Professor of Computer Science in the Paulson School of Engineering and Applied Sciences and Co-Director of the Harvard Data Science Initiative. His research focuses on artificial intelligence, machine learning, and microeconomic theory. A Fellow of the ACM and the AAAI, Parkes served on the inaugural panel of the “Stanford 100 Year Study on Artificial Intelligence,” co-organized the 2016 OSTP Workshop on “AI for Social Good,” and served as chair of the ACM SIG on Electronic Commerce (2011–16). Parkes is recipient of the 2017 ACM/SIGAI Autonomous Agents Research Award, the NSF Career Award, the Alfred P. Sloan Fellowship, the Thouron Scholarship, and Harvard’s Roslyn Abramson Award for Teaching. Parkes has degrees from the University of Oxford and the University of Pennsylvania, serves on several international scientific advisory boards, and advises a number of start-ups.

Comments are closed.