I’m a third year graduate student at Lab for Information and Decision Systems (LIDS) at MIT. I work with Prof. Guy Bresler on Applied Probability and Statistics.

I seek to solve theoretical machine learning problems([1]) using ideas from Probability Theory and Statistics and in the process, obtain novel insights into Probability Theory itself. I am currently devising methods to compare two different probability distributions over high dimensional spaces using associated Markov processes. I am also interested in understanding various local, randomized optimization algorithms.

Previously I was an undergraduate student at IIT Madras.


Email:
dheeraj[at]mit[dot]edu

 

[1] “आकाशात् पतितं तोयं यथा गच्छति सागरम्” 

 

Publications:

In Preparation:

  • Super-log optimal final point guarantees for non smooth Stochastic Gradient Descent. (2019)
    with Praneeth Netrapalli and Prateek Jain
  • Non-Asymptotic guarantees for smooth Random Reshuffling. (2019)
    with Praneeth Netrapalli and Prateek Jain
  • Total Variation Convergence of Random Graphs. (2019)
    with Matthew Brennan and Guy Bresler

Manuscripts:

  • Stein’s Method for Stationary Distributions of Markov Chains and Application to Ising Models. (2017)
    arXiv preprint, submitted to Annals of App. Probability
    with Guy Bresler
    Description: We give a method to bound the Wasserstein distance of binary random vectors by comparing their associated Glauber dynamics. The method is applied to show that two randomly picked sites in an Ising model over a d-regular expander graph behave very similar to two randomly picked sites over a Curie-Weiss model.

Conference Publications:

  • Optimal Single Sample Tests for Structured versus Unstructured Network Data. (2018)
    COLT 2018.
    arxiv preprint 

    with Guy Bresler
    Description: We give a general, optimal single sample test to distinguish between unstructured models (Curie-Weiss, Erdos-Renyi etc) to structured models (Ising model, Exponential Random Graphs etc) when temperature parameters are unknown. We use distributional approximation as the main tool to prove the guarantees of this test.

Journal Publications:

  •  Continuous limit of discrete quantum walks. (2015)
    Physical Review A, arxiv:1501.06950
    with Todd A. Brun
    Description: We give a general method to obtain continuous time analogues of discrete time quantum walks under certain assumptions by mapping it to a different space. We illustrate our method by showing that the grid-walk variant of Grover’s algorithm performs just as well in  continuous time as it does in the discrete time.

Talks:

Lids Student Conference 2017 : Comparing Structured and Unstructured Models.