Deepak Maurya

PhD Candidate

CSE Dept, Purdue University

Biography

I am currently a PhD candidate at CSE Dept, Purdue University, advised by Prof. Jean Honorio.

Before joining Purdue University, I was an MS (Research) scholar under the guidance of Prof. Balaraman Ravindran and Prof. Shankar Narasimhan at CSE department, IIT Madras. My MS work was focused on spectral hypergraph theory using tensor representation of hypergraphs.

I finished my Dual Degree (B.Tech + M.Tech) in Electrical Engineering from IIT Madras in 2016 where I collaborated with Prof. Arun K. Tangirala, Prof. Shankar Narasimhan for my final year research project. I am also fortunate for the opportunity to closely work with Prof. Raghunathan Rengaswamy, Prof. Manikandan Narayanan, and Prof. Srinivasan Parthasarathy.

Interests

Theoretical Machine Learning
Learning on Graphs / Hypergraphs
System Identification

Education

PhD in Computer Science, 2021

Purdue University
MS (Research) in Computer Science, 2018

Indian Institute of Technology Madras
B.Tech and M.Tech in Electrical Engg., 2011

Indian Institute of Technology Madras

News

Recent work accepted in AISTATS 2026: Robust Estimation of a Sparse Linear Model - Provable Guarantees with Non-convexity
Co-organized fifth edition of Graphs & more Complex structures for Learning & Reasoning (GCLR) workshop at AAAI. I have co-organized GCLR workshop five times.
Recent Work Accepted in ICASSP 2025: Exact solution for Adversarial Training and Partial Inference in Structured Prediction.
Work on Adversarial Corruption Accepted in TMLR: Adversarial Corruption on Sparse Regression.
Work Accepted in LoG 2023: Hypergraph Learning Enriched with Attributes and Layers (HEAL).
Work Accepted in Journal of Franklin Institute: ARX-EIV identification using DIPCA.

Publications

Deepak Maurya, Arun K. Tangirala, Shankar Narasimhan (2020). ARX Model Identification using Generalized Spectral Decomposition. In MTNS 2020.

PDF

Deepak Maurya, Sivadurgaprasad Chinta, Abhishek Sivaram, Raghunathan Rengaswamy (2020). Incorporating prior knowledge about structural constraints in model identification.

PDF

Chaithanya K. Donda, Deepak Maurya, Arun K. Tangirala, Shankar Narasimhan (2020). Identification of MISO systems in Minimal Realization Form. In ACODS 2020.

PDF

Vipul Mann, Deepak Maurya, Arun K. Tangirala, Shankar Narasimhan (2020). Optimal Filtering and Residual Analysis in Errors-in-Variables Model Identification. I&ECR.

PDF Code

Deepak Maurya, Balaraman Ravindran, Shankar Narasimhan (2019). Hypergraph Partitioning using Tensor Eigenvalue Decomposition. In NeurIPS 2019 Workshop.

PDF Poster Poster

Deepak Maurya, Balaraman Ravindran, Shankar Narasimhan (2019). Hyperedge Prediction using Tensor Eigenvalue Decomposition. In TMEDSC @ KDD 2019.

PDF Poster Slides Poster Slides