Dhruv Rohatgi

Hi! I'm a first-year graduate student in EECS at MIT, and am fortunate to be advised by Ankur Moitra. My current research interests are in computational learning theory and related topics: high-dimensional statistics, optimization, and theoretical machine learning.

I am grateful to be supported by an NDSEG Fellowship and an MIT Akamai Fellowship.

To reach me: [first initial][last name]@mit.edu

Publications and Preprints

  1. Learning in Observable POMDPs, without Computationally Intractable Oracles
    with Ankur Moitra and Noah Golowich
  2. Provably Auditing Ordinary Least Squares in Low Dimensions
    with Ankur Moitra
  3. Distributional Hardness Against Preconditioned Lasso via Erasure-Robust Designs
    with Jonathan Kelner, Frederic Koehler, and Raghu Meka
  4. Planning in Observable POMDPs in Quasipolynomial Time
    with Ankur Moitra and Noah Golowich
  5. Robust Generalized Method of Moments: A Finite Sample Viewpoint
    with Vasilis Syrgkanis
    Preliminary version selected for Oral Presentation at MLECON Workshop (NeurIPS 2021)
  6. On the Power of Preconditioning in Sparse Linear Regression
    with Jonathan Kelner, Frederic Koehler, and Raghu Meka
    FOCS 2021 ♦ 62nd Annual IEEE Symposium on Foundations of Computer Science.
  7. Truncated Linear Regression in High Dimensions
    with Costis Daskalakis and Manolis Zampetakis
    NeurIPS 2020 ♦ 34th Conference on Neural Information Processing Systems.
  8. Constant-Expansion Suffices for Compressed Sensing with Generative Priors
    with Costis Daskalakis and Manolis Zampetakis
    NeurIPS 2020 (Spotlight Presentation) ♦ 34th Conference on Neural Information Processing Systems.
  9. Regarding two conjectures on clique and biclique partitions
    with John C. Urschel and Jake Wellens
    The Electronic Journal of Combinatorics (2021).
  10. Near-Optimal Bounds for Online Caching with Machine-Learned Advice
    SODA 2020 ♦ 31st ACM-SIAM Symposium on Discrete Algorithms.
  11. Conditional Hardness for Approximate Earth Mover Distance
    APPROX 2019 ♦ 22nd Intl. Conference on Approximation Algorithms for Combinatorial Optimization Problems.
  12. Off-diagonal Ordered Ramsey Numbers of Matchings
    The Electronic Journal of Combinatorics (2019).

Authors are listed in alphabetical order, following the convention in mathematics and theoretical computer science.