Adel Javanmard
 |
Professor of Data Sciences and Operations (by courtesy) Department of Computer Science University of Southern California Sloan fellow in mathematics |
Contact
Office: 300A Bridge Hall, University of Southern California, Los Angeles, CA 90089
Tel: (213)821-4193
Email: ajavanma(at)usc.edu
Here are links to my Google Scholar Profile, LinkedIn Profile and a short bio in the third-person.
Prospective PhD students: If you have strong theoretical background in Statistics, optimization and machine learning, and are enthusiastic about pursuing a Ph.D. in Data Science at USC Marshall, please don't hesitate to get in touch. Share your CV and express your areas of interest with me.
CS Applicants: Admissions to the Ph.D. program are managed at the department level, and not by me personally. If you are currently a USC Computer Science Ph.D. student and are keen on collaborating with me, please reach out.
About Me
I am a Professor of Data Sciences and Operations, Marshall School of Business at the University of Southern California (USC). Due to strong overlap in research interests, I also hold a courtesy appointment at the Computer Science Department in the USC Viterbi School of Engineering. Prior to joining USC, I was NSF CSoI postdoctoral fellow with worksite at Stanford University and UC Berkeley. I obtained my Ph.D. in Electrical Engineering from Stanford University advised by Andrea Montanari.
I am broadly interested in design and analysis of statistical methods for large-scale data, high-dimensional inference, network analysis, non-convex optimization and personalized decision-making. Some of the topics that I have been working on in the past few years include:
Uncertainty-aware machine learning: Debiasing statical models, Predictive inference, Online hypothesis testing, Model evaluation and calibration
Theoretical understanding of deep learning: Iterative estimation, non-convex optimization, Adversarial robustness, Learning under distribution shift
Personalized decision making: Dynamic pricing and product assortment under feature-based valuation models, robustness against model misspecification, incentive-aware learning with strategic buyers, exploiting global shrinkage models to exploit customers network structure
Private learning: Reidentification attacks, Private causal inference, Aggregate learning, Look-alike clustering
I have been fortunate enough to receive a number of recognitions for my work, including the Alfred P. Sloan Research Fellow in Mathematics, the IMS Tweedie Researcher award, the NSF CAREER award, as well as industry grants and awards (Google, Adobe). See the Awards & Honors section for more details.
I have also been serving as an Associate Editor for Operations Research in the “Machine Learning and Data Science” department (since 2021), and the Dantzig Dissertation Prize Committee (2022-2023).
I have been teaching core courses in the undergraduate program (applied business statistics and operations management), and PhD special topics courses in modern statistical inference. In 2022, I received the Golden Apple Award for core classes, given each year to faculty who demonstrate, in their teaching and results, a significant, positive impact on the students’ growth and learning (selected by students’ votes).
Selected Publications
For the complete list of publications, check here (for publications by year) and here (for publications by topic).
Measuring Re-identification Risk
in collaboration with a great team at Google Research
ACM Journal on Management of Data (PACMMOD), 2023
ACM SIGMOD/PODS International Conference on Management of Data, 2023.
SecWeb workshop (Designing security for the Web), 2023
Precise Tradeoffs in Adversarial Training for Linear Regression
Adel Javanmard, Mahdi Soltanolkotabi, Hamed Hassani
Annual Conference on Learning Theory (COLT), 2020
Analysis of a Two-Layer Neural Network via Displacement Convexity
Adel Javanmard, Marco Mondelli, Andrea Montanari
Accepted for publication in Annals of Statistics, 2019
Dynamic Incentive-Aware Learning: Robust Pricing in Contextual Auctions
Negin Golrezaei, Adel Javanmard and Vahab Mirrokni
Accepted for publication in Operations Research, 2019.
(Preliminary version of this paper accepted to NeurIPS 2019.)
Theoretical insights into the optimization landscape of over-parameterized shallow neural networks
Mahdi Soltanolkotabi, Adel Javanmard and Jason D. Lee
in IEEE Transaction on Information Theory, 65(2), pages 742-769, 2018.
Phase Transitions in Semidefinite Relaxations [Website]
Adel Javanmard, Andrea Montanari and Federico Ricci-Tersenghi
In Proceedings of the National Academy of Sciences (PNAS), 113(16): E2218-E2223, 2016
Confidence Intervals and
Hypothesis Testing for High-Dimensional Regression [Website]
Adel Javanmard and Andrea Montanari
in Journal of Machine Learning Research, 15(1): 2869-2909, 2014.
Information-Theoretically Optimal Compressed Sensing via Spatial Coupling and Approximate Message Passing
David L. Donoho, Adel Javanmard, Andrea Montanari
IEEE Transaction on Information Theory, vol. 59, no. 11, pp 7434-7464, Nov 2013.