Raaz RSK Dwivedi

Coming soon! 

Postdoctoral Fellow
Harvard University
Massachusetts Institute of Technology

Harvard contact: raaz@seas.harvard.edu, 2.339, SEC Harvard SEAS
MIT contact: raaz@mit.edu, 32-D569, Stata Center

Google Scholar, Semantic Scholar, DBLP Profile

I am currently a FODSI postdoc fellow and fortunate to be co-advised by Prof. Susan Murphy in the Departments of Computer Science and Statistics at Harvard, and Prof. Devavrat Shah in the Laboratory of Information Decision and Systems (LIDS), Department of EECS at MIT. I recently finished my Ph.D. in the Department of EECS at the UC Berkeley where I was fortunate to be advised by Prof. Martin Wainwright and Prof. Bin Yu.

Short Bio

News

Recent talks

  • Kernel Thinning (paper 1, paper 2, slides, poster, code)

    • Alan Turing Institute: Invited talk at the Data-Centric Engineering Reading Group (DCE), Sep 2021

    • Harvard University Statistics Dept: Talk at Stat 300, Sep 2021

    • Monte Carlo Methods and Applications (MCM), Contributed talk, Sep, 2021

    • World Meeting of the International Society for Bayesian Analysis (ISBA), Contributed talk, Aug 2021

    • The Bayesian Young Statisticians Meeting (BAYSM), Contributed talk, Aug 2021

    • The Conference on Learning Theory (COLT), Contributed talk, Aug 2021

    • Subset Selection in Machine Learning Workshop, International Conference on Machine Learning (Subset ML, ICML), Contributed talk, July 2021

  • Revisiting Minimum Description Length Complexity in Overparameterized Models (paper, slides, poster)

    • Collaborations on the Theoretical Foundations of Deep Learning deepfoundations.ai, Invited talk, Nov 2021

    • IEEE North American School of Information Theory (NASIT), Contributed poster, June 2021

    • Workshop on the Theory of Overparameterized Machine Learning (TOPML), Contributed talk, Apr 2021

    • UC Berkeley, Guest Lecture in Stat 212 (Information theory and statistics), Apr 2021

  • Stable Discovery of Interpretable Subgroups in Causal Studies (paper, slides, poster)

    • Microsoft Research New England (MSR), Jan 2021

Detailed Bio

I received my Ph.D. in Summer 2021, from the Department of EECS at the University of California, Berkeley (UC Berkeley) where I was fortunate to be advised by Prof. Martin Wainwright and Prof. Bin Yu. My thesis committee members included Prof. David Aldous and Prof. Peter Bartlett. I was also fortunate to work with several collaborators, including Prof. Michael Jordan at UC Berkeley, Lester Mackey at Microsoft Research (MSR), and Prof. David Madigan at the Northeastern University (formerly at Columbia University). At Berkeley, I was associated with the Berkeley Laboratory for Information and System Sciences (BLISS), and the Berkeley Artificial Intelligence Research group (BAIR).

Research interests: My research interests include both the theoretical and applied aspects of statistical machine learning and data science. My recent works cover various topics in high-dimensional statistics with a focus on random sampling, improving sample quality. More recently, I have started thinking about problems at the intersection of reinforcement learning and causal inference.

Awards: At UC Berkeley, I was awarded the Outstanding Graduate Student Instructor Award in 2020. I also received the prestigious Berkeley Fellowship, the highest award for the incoming graduate students, in 2015. During my graduation at IIT Bombay, I was awarded the President of India Gold Medal, the highest honor to a graduating batch of students, the Institute Silver Medal for the highest GPA, and the Best B. Tech Project Award in the EE department.

Work experience: I spent the summer of 2019 as a research intern at Microsoft Research New England. I also spent the summer of 2017 as an intern at Mist systems, Cupertino (later acquired by Juniper Networks). Before joining UC Berkeley, I worked for a year at WorldQuant Research in Mumbai, India, as a Senior Quantitative Researcher. During my undergrad, I spent the summer of 2013 at Stanford University as an intern with Prof. Balaji Prabhakar, and the winter of 2012 at Ivy Mobility.

Pre-Ph.D. life: Before UC Berkeley, I graduated from the Indian Institute of Technology, Bombay (IIT Bombay), with a B. Tech. (Honors) in Electrical Engineering and Minors in Mathematics. At IIT Bombay, I was also fortunate to work with Prof. Vivek Borkar, Prof. Pradeep Nair, and Prof. Juzer Vasi.