Harshay Shah

I am a pre-doctoral research fellow at Microsoft Research India, where I work with Praneeth Netrapalli and Prateek Jain. I obtained my BS in Computer Science & Statistics from the University of Illinois at Urbana-Champaign (UIUC), where I was advised by Hari Sundaram, Sewoong Oh, and Sanmi Koyejo.

I am broadly interested in understanding deep learning phenomena through theory and experiments. My current research focuses on questions related to robust and reliable machine learning.


Do Input Gradients Highlight Discriminative Features?

Harshay Shah, Prateek Jain, and Praneeth Netrapalli
Preprint, arXiv:2102.12781(2021)

The Pitfalls of Simplicity Bias in Neural Networks

Harshay Shah, Kaustav Tamuly, Aditi Raghunathan, Prateek Jain, and Praneeth Netrapalli
Advances in Neural Information Processing Systems(NeurIPS 2020)
ICML Workshop on Uncertainty and Robustness in Deep Learning(ICML UDL 2020)

Growing Attributed Networks through Local Processes

Harshay Shah, Suhansanu Kumar, and Hari Sundaram
Proceedings of the World Wide Web Conference (WWW 2019)

Number of Connected Components in a Graph: Estimation via Counting Patterns

Ashish Khetan, Harshay Shah, and Sewoong Oh
Preprint, arXiv:1812.00139(2018)