Video URL

https://simons.berkeley.edu/talks/theoretical-foundations-data-driven-algorithm-design

Mechanism Design Via Machine Learning: Overfitting, Incentives, and Privacy

(2022). Mechanism Design Via Machine Learning: Overfitting, Incentives, and Privacy. The Simons Institute for the Theory of Computing. https://simons.berkeley.edu/talks/theoretical-foundations-data-driven-algorithm-design

Mechanism Design Via Machine Learning: Overfitting, Incentives, and Privacy. The Simons Institute for the Theory of Computing, Feb. 11, 2022, https://simons.berkeley.edu/talks/theoretical-foundations-data-driven-algorithm-design 

          @misc{ scivideos_19611,
            doi = {},
            url = {https://simons.berkeley.edu/talks/theoretical-foundations-data-driven-algorithm-design},
            author = {},
            keywords = {},
            language = {en},
            title = {Mechanism Design Via Machine Learning: Overfitting, Incentives, and Privacy},
            publisher = {The Simons Institute for the Theory of Computing},
            year = {2022},
            month = {feb},
            note = {19611 see, \url{https://scivideos.org/Simons-Institute/19611}}
          }
Ellen Vitercik (UC Berkeley)
Source Repository Simons Institute
Subject

Abstract

Machine learning is increasingly being used for mechanism design, with applications such as price optimization on online marketplaces and ad auction design. In this talk, I will give an overview of my research on mechanism design via machine learning, touching on statistical problems such as overfitting, incentive problems, and privacy preservation.