Adel Javanmard
Adel Javanmard | |
|---|---|
 | |
| Born | 1987 (age 38–39) |
| Alma mater | Stanford University Sharif University of Technology |
| Scientific career | |
| Fields | Statistics Artificial intelligence Machine Learning Data science |
| Thesis | Inference and estimation in high-dimensional data analysis |
Adel Javanmard (born 1987) is a professor in the fields of artificial intelligence, machine learning, statistics and data science. He has worked on high-dimensional statistics,[1] foundations of deep neural network, message passing, and differential privacy.[2] He is a professor of Data Sciences and Operations at the Marshall School of Business at the University of Southern California (USC).[3]
Early life and education
While in high school, Javanmard earned a gold medal in the National Mathematical Olympiad in 2003 and a silver medal at the 45th International Mathematical Olympiad (IMO) in 2004.[4] He completed his undergraduate studies with BSc degrees in electrical engineering and pure mathematics at Sharif University of Technology.[1] In 2014, he received his PhD in Electrical Engineering from Stanford University.[5] His PhD thesis, "Inference and estimation in high-dimensional data analysis" won the Thomas Cover dissertation award from IEEE Information Theory Society.[6]
Academic biography
After completing his doctorate, Javanmard was an NSF postdoctoral fellow at the Center for Science of Information with UC Berkeley, working with David Tse.[7] In 2015, he joined University of Southern California (USC) as a faculty member in the Data Sciences and Operations Department in the Marshall School of Business.[3]
Research
Javanmard has worked in high-dimensional statistics,[8] robust machine learning,[9] optimization,[10] network analysis,[11] personalized decision-making,[12] and private learning.[13]
Awards and honors
References
- 1 2 "Institute of Mathematical Statistics | IMS Tweedie Award Lecture: Adel Javanmard". Retrieved 2025-09-19.
- ↑ "Publications". faculty.marshall.usc.edu. Retrieved 2025-09-19.
- 1 2 3 "Adel Javanmard". USC Marshall School of Business. Retrieved 2025-09-19.
- ↑ "International Mathematical Olympiad". www.imo-official.org. Retrieved 2025-09-04.
- ↑ "Inference and estimation in high-dimensional data analysis". searchworks.stanford.edu. Retrieved 2025-09-19.
- ↑ "Member profile #9350 | IEEE Information Theory Society". www.itsoc.org. Retrieved 2025-09-19.
- ↑ "Former Postdocs | Tse Lab at Stanford University". tselab.stanford.edu. Retrieved 2025-09-19.
- ↑ Javanmard, Adel; Montanari, Andrea (2014). "Confidence intervals and hypothesis testing for high-dimensional regression" (PDF). The Journal of Machine Learning Research. 15 (1): 2869–2909.
- ↑ Javanmard, Adel; Soltanolkotabi, Mahdi; Hassani, Hamed (2020-07-15). "Precise Tradeoffs in Adversarial Training for Linear Regression". Proceedings of Thirty Third Conference on Learning Theory. PMLR: 2034–2078.
- ↑ Soltanolkotabi, Mahdi; Javanmard, Adel; Lee, Jason D. (February 2019). "Theoretical Insights Into the Optimization Landscape of Over-Parameterized Shallow Neural Networks". IEEE Transactions on Information Theory. 65 (2): 742–769. arXiv:1707.04926. Bibcode:2019ITIT...65..742S. doi:10.1109/TIT.2018.2854560. ISSN 1557-9654.
- ↑ Javanmard, Adel; Montanari, Andrea; Ricci-Tersenghi, Federico (2016-04-19). "Phase transitions in semidefinite relaxations". Proceedings of the National Academy of Sciences. 113 (16): E2218–E2223. arXiv:1511.08769. Bibcode:2016PNAS..113E2218J. doi:10.1073/pnas.1523097113. PMC 4843421. PMID 27001856.
- ↑ Javanmard, Adel; Nazerzadeh, Hamid (2019). "Dynamic Pricing in High-dimensions". Journal of Machine Learning Research. 20 (9): 1–49. ISSN 1533-7928.
- ↑ Carey, CJ; Dick, Travis; Epasto, Alessandro; Javanmard, Adel; Karlin, Josh; Kumar, Shankar; Muñoz Medina, Andres; Mirrokni, Vahab; Nunes, Gabriel Henrique; Vassilvitskii, Sergei; Zhong, Peilin (2023-06-20). "Measuring Re-identification Risk". Proceedings of the ACM on Management of Data. 1 (2): 1–26. doi:10.1145/3589294.
- ↑ "CAREER: Valid and Scalable Inference for High-dimensional Statistical Models".