I am the class of 1940 Bicentennial Term Associate Professor of Computer and Information Science at the University of Pennsylvania computer science department
, associated with the theory group
, PRiML (Penn Research in Machine Learning)
the Warren Center for Network and Data Sciences
, and am co-director of our program in Networked and Social Systems Engineering
. I am also affiliated with the AMCS
program (Applied Mathematics and Computational Science). I spent a year as a postdoc at Microsoft Research New England
. Before that, I received my PhD from Carnegie Mellon University
, where I was fortunate to have been advised by Avrim Blum
My main interests are in algorithms and machine learning,
and specifically in the areas of private data analysis, fairness in machine learning, game theory and mechanism design, and learning theory.
I am the recipient of a Presidential Early Career Award for Scientists and Engineers
), an Alfred P. Sloan Research Fellowship
, an NSF CAREER award, a Google Faculty Research Award, an Amazon Research Award, and a Yahoo Academic Career Enhancement award.
For more information, see my CV.
My lovely wife Cathy just got her PhD in math
at MIT. At her insistence, I link to her website
Office: 3401 Walnut Street, room 406b
Coming Fall 2019:
and I have written a
about the science of designing algorithms that embed social values like privacy and fairness; here is the publisher's description:
Over the course of a generation, algorithms have gone from mathematical abstractions to powerful mediators of daily life. Algorithms have made our lives more efficient, more entertaining, and, sometimes, better informed. At the same time, complex algorithms are increasingly violating the basic rights of individual citizens. Allegedly anonymized datasets routinely leak our most sensitive personal information; statistical models for everything from mortgages to college admissions reflect racial and gender bias. Meanwhile, users manipulate algorithms to "game" search engines, spam filters, online reviewing services, and navigation apps.
Understanding and improving the science behind the algorithms that run our lives is rapidly becoming one of the most pressing issues of this century. Traditional fixes, such as laws, regulations and watchdog groups, have proven woefully inadequate. Reporting from the cutting edge of scientific research, The Ethical Algorithm offers a new approach: a set of principled solutions based on the emerging and exciting science of socially aware algorithm design. Michael Kearns and Aaron Roth explain how we can better embed human principles into machine code - without halting the advance of data-driven scientific exploration. Weaving together innovative research with stories of citizens, scientists, and activists on the front lines, The Ethical Algorithm offers a compelling vision for a future, one in which we can better protect humans from the unintended impacts of algorithms while continuing to inspire wondrous advances in technology.
This semester I am teaching CIS 262: Automata, Computability, and Complexity
I'm fortunate to be able to work with several excellent graduate students and postdocs.
Books and Surveys
- Bo Waggoner (Warren Center Postdoctoral Fellow). Microsoft Research NYC -> University of Colorado Boulder
- Jamie Morgenstern (Warren Center Postdoctoral Fellow). Georgia Tech CS
- Justin Hsu (PhD student co-advised with Benjamin Pierce). UCL/Cornell -> University of Wisconsin. (John C. Reynolds Doctoral Dissertation Award)
- Steven Wu (PhD student co-advised with Michael Kearns). Microsoft Research NYC -> University of Minnesota. (Morris and Dorothy Rubinoff Award for Best Thesis)
- Ryan Rogers (PhD student co-advised with Michael Kearns). LinkedIn
- Zhiyi Huang (PhD student co-advised with Sampath Kannan). Stanford -> University of Hong Kong. (Morris and Dorothy Rubinoff Award for Best Thesis)
- Kris Iyer (Postdoc, jointly hosted with Michael Kearns and Mallesh Pai). Cornell ORIE.
- Yang Jiao (BS/MS student). PhD student at CMU
- Rachel Cummings (Visiting PhD student) Georgia Tech ISYE
Recent and Selected Publications
- The Ethical Algorithm. Joint with Michael Kearns. Oxford University Press, Forthcoming Fall 2019.
- The Algorithmic Foundations of Differential Privacy. Joint with Cynthia Dwork. Foundations and Trends in Theoretical Computer Science, NOW Publishers. 2014.
- Privacy and Mechanism Design. Joint with Mallesh Pai. SIGecom Exchanges, 2013.
for all publications, or my Google Scholar profile
Click for abstract/informal discussion of
- The Role of Interactivity in Local Differential Privacy. Joint work with Matthew Joseph, Jieming Mao, and Seth Neel. Manuscript.
- Equal Opportunity in Online Classification with Partial Feedback. Joint with Yahav Bechavod, Katrina Ligett, Bo Waggoner, and Steven Wu. Manuscript.
- How to Use Heuristics for Differential Privacy. Joint with Seth Neel and Steven Wu. Manuscript.
- The Frontiers of Fairness in Machine Learning. Joint with Alexandra Chouldechova. CCC Workshop Report.
- Fair Algorithms for Learning in Allocation Problems. Joint with Hadi Elzayn, Shahin Jabbari, Christopher Jung, Michael Kearns, Seth Neel, and Zachary Schutzman. In the Proceedings of FAT* 2019.
- The Downstream Effects of Affirmative Action. Joint with Sampath Kannan and Juba Ziani. In the Proceedings of FAT* 2019.
- An Empirical Study of Rich Subgroup Fairness for Machine Learning. Joint with Michael Kearns, Seth Neel, and Steven Wu. In the Proceedings of FAT* 2019.
- Local Differential Privacy for Evolving Data. Joint with Matthew Joseph, Jon Ullman, and Bo Waggoner. In the proceedings of NIPS 2018.
- Online Learning with an Unknown Fairness Metric. Joint with Stephen Gillen, Christopher Jung, and Michael Kearns. In the proceedings of NIPS 2018.
- A Smoothed Analysis of the Greedy Algorithm for the Linear Contextual Bandit Problem. Joint with Sampath Kannan, Jamie Morgenstern, Bo Waggoner, and Steven Wu. In the proceedings of NIPS 2018.
- Mitigating Bias in Adaptive Data Gathering via Differential Privacy. Joint with Seth Neel. In the proceedings of ICML 2018.
- Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness. Joint with Michael Kearns, Seth Neel, and Steven Wu. In the proceedings of ICML 2018.
- Strategic Classification from Revealed Preferences. Joint with Jinshuo Dong, Zachary Schutzman, Bo Waggoner, and Steven Wu. In the proceedings of EC 2018.
- Multidimensional Dynamic Pricing for Welfare Maximization. Joint with Alex Slivkins, Jon Ullman and Steven Wu. In the proceedings of EC 2017.
- Fairness in Learning: Classic and Contextual Bandits. Joint with Matthew Joseph, Jamie Morgenstern, and Michael Kearns. In the proceedings of NIPS 2016.
- Robust Mediators in Large Games. Joint with Michael Kearns, Mallesh Pai, Ryan Rogers, and Jon Ullman. Manuscript. (This paper subsumes both "Mechanism Design in Large Games: Incentives and Privacy" which appeared in ITCS 2014, and "Asymptotically Truthful Equilibrium Selection" which appeared in EC 2014).
- Max-Information, Differential Privacy, and Post-Selection Hypothesis Testing. Joint with Ryan Rogers, Adam Smith, and Om Thakkar. In the proceedings of FOCS 2016.
- Do Prices Coordinate Markets?. Joint work with Justin Hsu, Jamie Morgenstern, Ryan Rogers, and Rakesh Vohra. In the proceedings of STOC 2016.
- Watch and Learn: Optimizing from Revealed Preferences Feedback. Joint with Jon Ullman and Steven Wu. In the proceedings of STOC 2016.
- Private Algorithms for the Protected in Social Network Search. Joint with Michael Kearns, Steven Wu, and Grigory Yaroslavtsev. In Proceedings of the National Academy of Sciences (PNAS), January 2016.
- Jointly Private Convex Programming. Joint work with Justin Hsu, Zhiyi Huang, and Steven Wu. In the proceedings of SODA 2016.
- The Reusable Holdout: Preserving Validity in Adaptive Data Analysis. Joint work with Cynthia Dwork, Vitaly Feldman, Moritz Hardt, Toniann Pitassi, and Omer Reingold. In Science, August 7 2015.
- Preserving Statistical Validity in Adaptive Data Analysis. Joint work with Cynthia Dwork, Vitaly Feldman, Moritz Hardt, Toniann Pitassi, and Omer Reingold. In the proceedings of STOC 2015.
- Approximately Stable, School Optimal, and Student-Truthful Many-to-One Matchings (via Differential Privacy). Joint with Sampath Kannan, Jamie Morgenstern, and Steven Wu. In the proceedings of SODA 2015.
- Private Matchings and Allocations. Joint work with Justin Hsu, Zhiyi Huang, Tim Roughgarden, and Steven Wu. In the proceedings of STOC 2014.
- Differential Privacy for the Analyst via Private Equilibrium Computation. Joint with Justin Hsu and Jon Ullman. In the proceedings of STOC 2013.
- Privately Releasing Conjunctions and the Statistical Query Barrier. Joint with Anupam
Gupta, Moritz Hardt, and Jonathan Ullman. In the proceedings of STOC 2011.
Full version appears in SIAM Journal on Computing (SICOMP) 2013.
- Selling Privacy at Auction. Joint work with Arpita Ghosh. In the proceedings of EC 2011.
Invited to a special issue of Games and Economic Behavior (GEB) 2013.
- Interactive Privacy via the Median Mechanism.
Joint with Tim
Roughgarden. In the proceedings of STOC 2010.
- A Learning
Theory Approach to Non-Interactive Database
Privacy. Joint with Avrim
Ligett. In the proceedings
of STOC 2008: The 40th ACM Symposium on the Theory of Computing.
Full version appears in Journal of the ACM (JACM) 2013.
Minimization and the Price of Total Anarchy. Joint
with Avrim Blum, MohammadTaghi
Katrina Ligett. In the
proceedings of STOC 2008: The 40th ACM Symposium on the Theory of
Workshops, Tutorials, Interviews, and Panels:
- An Abridged Introduction to Differential Privacy February 17, 2019. The Annual Meeting of the American Association for the Advancement of Science (AAAS) (Tutorial)
- Philadelphia Symposium on Research Credibility, Panel on Data Interpretation and Credibility.
- Simons Institute Adaptive Data Analysis Workshop, Berkeley, CA. July 24-25, 2018. (Co-organizers Cynthia Dwork, Adam Smith, Weijie Su, James Zou). Tutorial Videos: Part 1 (Aaron), Part 2 (Adam)
- 6 hour mini-course on (un)fairness in machine learning, as part of the University of Zurich Machine Learning Summer School. June 29, 2018. Slides here.
- Northwestern Quarterly Theory Workshop: Algorithmic Fairness. June 8, 2018. (Co-organizer: Jason Hartline)
- In Conversation with the Rosenbach: Flash Focus on Privacy and the Internet. May 17, 2018.
- Differential Privacy Interview with ``This Week in Machine Learning'' (TWIML). (Click for audio). April 30, 2018.
- Penn Teach In Panel: "The Future of Technology: Artificial Intelligence and Society". Video here. Philadelphia, March 20 2018.
- CCC Workshop on Fair Representations and Fair Interactive Learning. Philadelphia, March 18-19 2018. (Co-organizer Alexandra Chouldechova)
- Fairness for Digital infrastructure. University of Pennsylvania, January 19-20, 2017.
- Tutorial on Machine Learning and Unfairness (Part of the Optimizing Government series). September 22, 2016. (video.)
- NIPS 2016 Workshop on Adaptive Data Analysis, held in conjunction with NIPS 2016. (Co-organizers: Adam Smith, Vitaly Feldman, Aaditya Ramdas)
- Invited ICML 2016 Tutorial: Rigorous Data Dredging: Theory and Tools for Adaptive Data Analysis. June 19, 2016. (Slides (Powerpoint) and video.)
- Nexus of Information and Computation: Security and Privacy March 21-April 1 2016. (Co-organizers: Prakash Narayan, Anand Sarwate,Vinod Vaikuntanathan, Salil Vadhan).
- NIPS 2015 Workshop on Adaptive Data Analysis, held in conjunction with NIPS 2015. (Co-organizers: Adam Smith, Vitaly Feldman, Moritz Hardt)
- The First Workshop on Algorithmic Game Theory and Data Science, held in conjunction with EC, June 15, 2015. (Co-organizers: Shuchi Chawla, Hu Fu, Jason Hartline, Denis Nekipelov, Kane Sweeney)
- An Introduction to Differential Privacy February 14, 2015. The Annual Meeting of the American Association for the Advancement of Science (AAAS) (Tutorial)
- Tutorial on Privacy, Information Economics, and Mechanism Design, held in conjunction with EC, June 9, 2014. (Co-tutors: Cynthia Dwork and Mallesh Pai)
- Workshop on Privacy and Economics, held in Conjunction with EC June 16, 2013. (Organized together with Katrina Ligett)
- Differential Privacy and Economics and the Social Sciences March 7, 2013. Open to the public! (Tutorial)
- DIMACS Workshop on Recent Work on Differential Privacy across Computer Science Oct. 24-26, 2012. (Organized together with Adam Smith)
- New York Computer Science and Economics Day V: The Economics of Big Data, Information, and Privacy. (Organized together with Dirk Bergemann, Sham Kakade, and Nitish Korula)
Program Committee Member For:
- ACM Symposium on Computer Science and Law, 2019.
- STOC 2019
- AAAI 2019 (Senior Program Committee)
- NIPS 2018 (Area Chair)
- ICML 2018 (Area Chair)
- FATML 2017, FAT* 2018 (Theory and Security Track Chair), FAT* 2019 (Theory and Security Track Chair).
- WWW 2018 ``Economics and Markets'' (Track Chair)
- NIPS Symposium on Machine Learning and the Law 2016
- COLT 2016, COLT 2017
- ITCS 2016
- Random 2015
- NetEcon 2015 (PC chair)
- TPDP 2015 (Organizing Committee), TPDP 2016
- WINE 2013, WINE 2014
- PODS 2013
- SODA 2013
- GameSec 2012
- FOCS 2012, FOCS 2014
- EC 2011, 2012, 2013, 2014, 2015, 2016 (SPC), 2017, 2018, 2019 (SPC)
(Slides Available Upon Request)
- The Role of Interactivity in Local Differential Privacy.
- Simons Institute Workshop on Privacy and the Science of Data Analysis. April 2019. Video here.
- The Ethical Algorithm.
- MIT Statistics and Data Science Conference. April 2019. Video here.
- The New York Academy of Sciences 13th Annual Machine Learning Day. Keynote Address. March 2019. Video here.
- Ethical Algorithms.
- Wharton Research Advisory Group. November 2018.
- Warren Center Symposium: The "FATE" Of Technology. October 2018.
- Distinguished Guest Lecture at the 8th Annual FDIC Consumer Research Symposium. October 2018.
- Wharton Conference on Digitization of Human Resources. September 2018.
- ``AI With the Best'' Developer Conference. September 2018. Video here.
- How to Use Heuristics for Differential Privacy.
- Princeton Computer Science Theory Seminar. March 2019. Video here.
- Wharton Statistics Student Seminar. December 2018.
- Keller Colloquium in Computing and Mathematical Sciences, Caltech. November 2018.
- Harvard Theory of Computation Seminar. November, 2018.
- Google AI NYC Theory Seminar. October 2018.
- Simons Workshop on Adaptive Data Analysis. July 2018.
- Algorithmic Approaches to Preventing Overfitting in Adaptive Data Analysis.
- (Un)fairness in Machine Learning. 6 hour version.
- University of Zurich Machine Learning Summer School. June, 2018. Slides here.
- Preventing Fairness Gerrymandering in Machine Learning.
- Purdue CS Department Colloquium ("CS Excellence Series"). November, 2018.
- Google ML Fairness Workshop. September, 2018.
- Facebook. September, 2018.
- Northwestern Quarterly Theory Workshop: Algorithmic Fairness. June, 2018.
- 6th Annual Computer Science and Law Roundtable, Penn Law School. May, 2018.
- Computational Perspectives on Biology and the Scientific Method.
- "Towards a New Theoretical Biology" Workshop, University of Pennsylvania. April, 2018.
- Privacy and Fairness: Explaining Problems and Technical Solutions.
- National Academy of Science, Roundtable on Integrating Ethics and Privacy Concerns into Data Science Education. December, 2017.
- A Smoothed Analysis of the Greedy Algorithm for Linear Contextual Bandits.
- Microsoft Research, New York City. July, 2017.
- Weakly Meritocratic Fairness in Machine Learning
- GREAT: Greece Workshop on Economic and Algorithmic Theory. July, 2017.
- Simons Differential Privacy Planning Workshop. May, 2017.
- Approximately Stable, School Optimal, Student-Truthful Many-to-One Matchings (via Differential Privacy)
- University of Wisconsin Economics Department Theory Seminar. November, 2017.
- Simons Differential Privacy Planning Workshop. May, 2017.
- MATCH-UP 2017. April, 2017.
- Fairness in Learning: Classic and Contextual Bandits.
- Stanford RAIN Seminar. April, 2017.
- MIT EECS Theory of Computation Colloquium. February, 2017.
- Institute for Advanced Study Computer Science and Discrete Math Seminar. January, 2017. (video.)
- Tradeoffs Between Fairness and Accuracy in Machine Learning
- NIPS Symposium on Machine Learning and the Law 2016. December, 2016.
- Harvard Law School, "Defining Fairness" Workshop. November, 2016.
- Yale Econ/CS Seminar ("Designing the Digital Economy") (Slides)
- What is Machine Learning (And Why Might it be Unfair?)
- Penn Law School. September, 2016. (video)
- Department of Defense/Department of Veterans Affairs Predictive Analytics and Suicide Risk Research Roundtable. February, 2018.
- Rigorous Data Dredging: Theory and Tools for Adaptive Data Analysis
- Joint Statistical Meetings: Session on the Stability Principle. August, 2017.
- Goldman Sachs Engineering Insights Series. February, 2017.
- NIPS 2016 Workshop on Adaptive Data Analysis. December, 2016.
- Institute for Advanced Study: Four Facets of Differential Privacy. November, 2016. (video here)
- Universite Laval Big Data Colloqium. October, 2016.
- Penn Statistics Department Seminar. September, 2016.
- PCMI Graduate Summer School: The Mathematics of Data. Park City, Utah. July 2016.
- Data Linkage and Anonymization Kickoff Event, Isaac Newton Center, Cambridge UK. July 2016.
- ICML 2016 Tutorial (Slides (Powerpoint) and video)
- A Whirlwind Tour of Differential Privacy (With Applications to Generalization and Game Theory)
- Google Research, New York, 2016.
- When do Prices Coordinate Markets?
- Penn State Theory Seminar, 2015.
- Workshop on Complexity and Simplicity in Economics, Simons Institute for the Theory of Computing, 2015. (video here)
- Harvard CRCS (Center for Research on Computation and Society) Seminar, 2015. (video here)
- Privacy as a Tool for Robust Mechanism Design in Large Markets
- PCMI Graduate Summer School: The Mathematics of Data. Park City, Utah. July 2016.
- Caltech Workshop on the Theory of Bringing Privacy into Practice, 2015. (video here)
- Private Convex Optimization (Yields Asymptotically Truthful Combinatorial Auctions)
- Cornell Joint Microeconomics and Computer Science Theory Seminar, 2014.
- Penn State Department Colloquium, 2014.
- NIPS Workshop on Transactional Machine Learning, 2014.
- ISMP 2015 Invited Speaker, 2015.
- Preserving Statistical Validity in Adaptive Data Analysis
- MIT/MSR Theory Day, 2014.
- Yahoo Research NYC Theory Seminar, 2014.
- Johns Hopkins Theory Seminar, 2014.
- TCS+ seminar, 2015. (video here)
- Bloomberg Research, Princeton Campus, 2015.
- BICOD 2015 Invited Lecture, 2015.
- Clinical Epidemiology/Health Services Research Seminar, Penn Medical School, 2015.
- Penn Applied Mathematics and Computational Science (AMCS) Colloquium. 2015.
- Private Matchings and Allocations
- Allerton 2013
- Charles River Privacy Day 2013
- Princeton Theory Lunch 2013
- Rutgers Theory Seminar 2014
- Tutorial on Differential Privacy
- Simons Workshop on the Science of Differential Privacy 2013
- American Association for the Advancement of Science (AAAS) Annual Meeting 2015 (see coverage)
- MLConf NYC 2017. (video here.)
- Hot Topics on the Science of Security (HoTSoS 2017) Keynote Talk.
- High Confidence Software and Systems Conference (HCSS 2017) Keynote Talk.
- MIT LIDS Smart Urban Infrastructures Workshop. 2017.
- Comcast Security Guild. December 2018.
- Security by the Schuylkill 2019 (Plenary Talk). April 2019.
- Tutorial on Game Theory and Differential Privacy
- WPin+NetEcon 2014
- EC 2014 Tutorial on Differential Privacy, Mechanism Design, and Information Economics
- EC 2013 Workshop on Differential Privacy and Mechanism Design
- DIMACS Differential Privacy Workshop 2012. (video here)
- Mechanism Design in Large Games: Privacy and Incentives
- FOCS 2012 PC Workshop
- USC Theory Seminar
- IBM TJ Watson Theory Seminar
- University of Maryland Capital Area Theory Seminar
- DIMACS Differential Privacy Workshop
- Stanford Market Design Seminar
- DIMACS Workshop on the Economics of Information Sharing
- Dagstuhl Workshop on the Frontiers of Mechanism Design.
- Caltech Workshop on Differential Privacy and Economics
- Exploiting Metric Structure for Efficient Private Query Release
- UCSD IDASH Differential Privacy Workshop
- Privately Releasing Conjunctions and the Statistical Query Barrier
- Microsoft Research Silicon Valley
- Penn State Theory Seminar
- MIT Theory Seminar
- Selling Privacy at Auction
- Northwestern EECS Theory Seminar
- Boston University Theory Seminar
- Interactive Privacy via the Median Mechanism
- STOC 2010
- Dartmouth Theory Seminar
- Efficient Computation Under the Constraints of Privacy And Incentives
- CMU Theory Seminar 2010
- UPenn Market and Social Systems Engineering Lecture Series 2010
- Yahoo Research, Santa Clara 2010
- On the Equilibria of Asynchronous Games
- Microsoft Research SVC
- CMU Theory Lunch
- China Theory Week 2009
- SODA 2010
- Differentially Private Approximation Algorithms
- Microsoft Research New England
- CMU Theory Lunch
- Princeton Theory Lunch
- SODA 2010
- Auctions with Online Supply
- EC 2010
- Ad Auctions Workshop 2009
- CMU Theory Lunch
- Microsoft Research SVC
- A Learning Theory Approach to Non-Interactive Database
- Microsoft Live Labs Tech Talk
- STOC 2008
- Capital Area Theory Seminar (University of Maryland)
- CMU/Microsoft Privacy Mindswap (Poster)
- Regret Minimization and the Price of Total Anarchy
- CMU Theory lunch
- GAMES 2008: 3rd World Congress of the Game Theory Society
- Harvard EconCS seminar
- ISMP 2009