Adarsh Barik

Contact

Lawson 2149 #28
Department of Computer Science
Purdue University
Email: abarik(at)purdue(dot)edu

About Me

I am a PhD student in Department of Computer Science at Purdue University. I am advised by Prof. Jean Honorio. Before coming to Purdue, I completed my B.Tech and M.Tech (Dual Degree) from Indian Institute of Technology, Madras.

Research Interests

I am interested in theoretical and computational aspect of Optimization, Machine Learning, Information Theory and High Dimensional Data Analytics.

Recently, I have been working in developing provable efficient techniques to recover graph structures from data. I work with both directed and undirected graphical models in high dimensional settings (in terms of number of nodes). My focus is to provide sufficient and necessary theoretical bounds on sample complexity and computational complexity for structure learning in graphs.

Publications

  1. Exact Support Recovery in Federated Regression with One-shot Communication
    Adarsh Barik, Jean Honorio
    Under submission
  2. Provable Sample Complexity Guarantees for Learning of Continuous-Action Graphical Games with Nonparametric Utilities
    Adarsh Barik, Jean Honorio
    Under submission
  3. Provable Computational and Statistical Guarantees for Efficient Learning of Continuous-Action Graphical Games
    Adarsh Barik, Jean Honorio
    Under submission
  4. Information Theoretic Limits for Standard and One-Bit Compressed Sensing with Graph-Structured Sparsity
    Adarsh Barik, Jean Honorio
    Under submission
  5. Fair Sparse Regression with Clustering: An Invex Relaxation for a Combinatorial Problem
    Adarsh Barik, Jean Honorio
    Accepted (Spotlight), NeurIPS 2021
  6. Information-Theoretic Bounds for Integral Estimation
    Donald Q. Adams, Adarsh Barik, Jean Honorio
    Accepted, ISIT 2021
  7. Learning Discrete Bayesian Networks in Polynomial Time and Sample Complexity
    Adarsh Barik, Jean Honorio
    Accepted, ISIT 2020
  8. Learning Bayesian Networks with Low Rank Conditional Probability Tables
    Adarsh Barik, Jean Honorio
    Accepted, NeurIPS 2019
  9. Information Theoretic Limits for Linear Prediction with Graph-Structured Sparsity
    Adarsh Barik, Jean Honorio, Mohit Tawarmalani
    Accepted, ISIT 2017

Teaching