Ambuj Tewari

Associate Professor

Department of Statistics

Department of Electrical Engineering and Computer Science (by courtesy)

University of Michigan, Ann Arbor

*tewaria@umich.edu*

In Every City, There's a George Floyd

My research group is engaged in fundamental research in the following areas:

- Statistical learning theory: We are developing theory and algorithms for predictions problems (e.g., learning to rank and multilabel learning) with complex label spaces and where the available human supervision is often weak. Another focus is on dependent and/or non-stationary data (such as in time series applications)
- Sequential prediction in a game theoretic framework: We are trying to understand the power and limitations of sequential prediction algorithms when no probabilistic assumptions are placed on the data generating mechanism.
- High dimensional and network data analysis: We are developing scalable algorithms with provable performance guarantees for learning from high dimensional and network data.
- Optimization algorithms: We are creating incremental, distributed and parallel algorithms for machine learning problems arising in today's data rich world.
- Reinforcement learning: We are synthesizing and further developing concepts and techniques from artificial intelligence, control theory and operations research for pushing forward the frontier in sequential decision making with a focus on delivering personalized health interventions via mobile devices. Here is a short video from a talk I gave at NYAS and an article from ISR Sampler. A related seminar series that I ran during 2013-2018 is archived here.

My alma maters are IIT Kanpur (B.Tech., 2002) and UC Berkeley (M.A., 2005 and Ph.D., 2007. Advisor: Peter Bartlett). I was a research assistant professor at TTIC from 2008 to 2010. From 2010 to 2012, I was a post-doctoral fellow at UT Austin where I worked with Inderjit Dhillon and Pradeep Ravikumar.

My younger brother Anuj Tewari is a Research Manager at Facebook.

I am one of the organizers of a semester long program on the Theory of Reinforcement Learning that will run during Fall 2020 at the Simons Institute for the Theory of Computing.

Activities at U-M I'm involved with:

- Academic Innovation at Michigan
- Michigan Institute for Data Science (MIDAS)
- MIDAS Project: Identifying Real-Time Data Predictors of Stress and Depression Using Mobile Technology
- NSF grant RTG: Understanding dynamic big data with complex structure
- Precision Health Initiative

Teaching

Publications ( Google Scholar, Semantic Scholar, arXiv, DBLP )

Talks

Code

Office Info

270 West Hall

1085 South University

Ann Arbor, MI 48109-1107

USA

Phone: +1-734-615-0928

Fax: +1-734-763-4676