Timezone: »
Designing an incentive compatible auction that maximizes expected revenue is an intricate task. The single-item case was resolved in a seminal piece of work by Myerson in 1981. Even after 30-40 years of intense research the problem remains unsolved for seemingly simple multi-bidder, multi-item settings. In this work, we initiate the exploration of the use of tools from deep learning for the automated design of optimal auctions. We model an auction as a multi-layer neural network, frame optimal auction design as a constrained learning problem, and show how it can be solved using standard pipelines. We prove generalization bounds and present extensive experiments, recovering essentially all known analytical solutions for multi-item settings, and obtaining novel mechanisms for settings in which the optimal mechanism is unknown.
Author Information
Paul Duetting (London School of Economics)
Zhe Feng (Harvard University)
Harikrishna Narasimhan (Google Research)
David Parkes (Harvard University)
Sai Srivatsa Ravindranath (Harvard University)
Related Events (a corresponding poster, oral, or spotlight)
-
2019 Oral: Optimal Auctions through Deep Learning »
Tue. Jun 11th 06:40 -- 07:00 PM Room Room 102
More from the Same Authors
-
2020 : Contributed Talk: From Predictions to Decisions: Using Lookahead Regularization »
Nir Rosenfeld · Sai Srivatsa Ravindranath · David Parkes -
2023 Poster: Oracles and Followers: Stackelberg Equilibria in Deep Multi-Agent Reinforcement Learning »
Matthias Gerstgrasser · David Parkes -
2021 Poster: Learning Representations by Humans, for Humans »
Sophie Hilgard · Nir Rosenfeld · Mahzarin Banaji · Jack Cao · David Parkes -
2021 Spotlight: Learning Representations by Humans, for Humans »
Sophie Hilgard · Nir Rosenfeld · Mahzarin Banaji · Jack Cao · David Parkes -
2021 Poster: Optimizing Black-box Metrics with Iterative Example Weighting »
Gaurush Hiranandani · Jatin Mathur · Harikrishna Narasimhan · Mahdi Milani Fard · Sanmi Koyejo -
2021 Poster: Implicit rate-constrained optimization of non-decomposable objectives »
Abhishek Kumar · Harikrishna Narasimhan · Andrew Cotter -
2021 Spotlight: Implicit rate-constrained optimization of non-decomposable objectives »
Abhishek Kumar · Harikrishna Narasimhan · Andrew Cotter -
2021 Spotlight: Optimizing Black-box Metrics with Iterative Example Weighting »
Gaurush Hiranandani · Jatin Mathur · Harikrishna Narasimhan · Mahdi Milani Fard · Sanmi Koyejo -
2021 Poster: Reserve Price Optimization for First Price Auctions in Display Advertising »
Zhe Feng · Sébastien Lahaie · Jon Schneider · Jinchao Ye -
2021 Poster: Fairness and Bias in Online Selection »
Jose Correa · Andres Cristi · Paul Duetting · Ashkan Norouzi-Fard -
2021 Spotlight: Fairness and Bias in Online Selection »
Jose Correa · Andres Cristi · Paul Duetting · Ashkan Norouzi-Fard -
2021 Oral: Reserve Price Optimization for First Price Auctions in Display Advertising »
Zhe Feng · Sébastien Lahaie · Jon Schneider · Jinchao Ye -
2020 Poster: The Intrinsic Robustness of Stochastic Bandits to Strategic Manipulation »
Zhe Feng · David Parkes · Haifeng Xu -
2020 Poster: Optimizing Black-box Metrics with Adaptive Surrogates »
Qijia Jiang · Olaoluwa Adigun · Harikrishna Narasimhan · Mahdi Milani Fard · Maya Gupta -
2019 Poster: Fairness without Harm: Decoupled Classifiers with Preference Guarantees »
Berk Ustun · Yang Liu · David Parkes -
2019 Oral: Fairness without Harm: Decoupled Classifiers with Preference Guarantees »
Berk Ustun · Yang Liu · David Parkes -
2019 Poster: Learning to Collaborate in Markov Decision Processes »
Goran Radanovic · Rati Devidze · David Parkes · Adish Singla -
2019 Poster: Metric-Optimized Example Weights »
Sen Zhao · Mahdi Milani Fard · Harikrishna Narasimhan · Maya Gupta -
2019 Oral: Learning to Collaborate in Markov Decision Processes »
Goran Radanovic · Rati Devidze · David Parkes · Adish Singla -
2019 Oral: Metric-Optimized Example Weights »
Sen Zhao · Mahdi Milani Fard · Harikrishna Narasimhan · Maya Gupta