G630, 32 Vassar Street
Stata Center, MIT
Cambridge, MA 02139
shibani AT mit DOT edu
My CV (last updated 11/26/2018)I am a PhD student in Computer Science at MIT, where I am fortunate to be co-advised by Aleksander Madry and Nir Shavit. My goal is to develop machine learning tools that are robust, reliable and ready for real-world deployment. Specifically, my research has been focused on two broad themes: developing a precise understanding of the functioning of widely-used deep learning techniques; and avenues to make machine learning methods robust and secure from an adversarial viewpoint.
Before coming to MIT, I graduated from Indian Institute of Technology Bombay in 2015 with a Dual Degree (Bachelors and Masters) in Electrical Engineering. For my Master's Thesis, I worked with Bipin Rajendran on artificial neural networks.
I spent the summer of 2018 at Google Brain, working with Ilya Mironov on developing differentially private generative models. During Summer '17, I was an intern at Vicarious with Huayan Wang.
In my free time, I learn classical dance (Odissi), and I am an amateur potter. I also contribute to the MadryLab blog.
Are Deep Policy Gradient Algorithms Truly Policy Gradient Algorithms?
Andrew Ilyas*, Logan Engstrom*, Shibani Santurkar, Dimitris Tsipras, Firdaus Janoos, Larry Rudolph, Aleksander Madry
[Blog posts: part 1 and part 2]
Robustness May Be at Odds with Accuracy
Dimitris Tsipras*, Shibani Santurkar*, Logan Engstrom*, Alexander Turner, Aleksander Madry
ICLR 2019
How Does Batch Normalization Help Optimization?
Shibani Santurkar*, Dimitris Tsipras*, Andrew Ilyas*, Aleksander Madry
NeurIPS 2018 (Oral Presentation)
[Blog post] , [Short video]
Adversarially Robust Generalization Requires More Data
Ludwig Schmidt, Shibani Santurkar, Dimitris Tsipras, Kunal Talwar, Aleksander Madry
NeurIPS 2018 (Spotlight Presentation)
A Classification-Based Study of Covariate Shift in GAN Distributions
Shibani Santurkar, Ludwig Schmidt, Aleksander Madry
ICML 2018
Generative Compression
Shibani Santurkar, David Budden, Nir Shavit
PCS 2018
Deep Tensor Convolution on Multicores
David Budden, Alex Matveev, Shibani Santurkar, Shraman Chaudhari, Nir Shavit
ICML 2017
C.elegans chemotaxis inspired neuromorphic circuit for contour tracking and obstacle avoidance
Shibani Santurkar, Bipin Rajendran
IJCNN 2015
Toward Streaming Synapse Detection with Compositional ConvNets
Shibani Santurkar, Alex Matveev, Yaron Meirovitch, David Budden, Hayk Saribekyan, Nir Shavit
Oral presentation at NIPS 2016 Connectomics workshop
* Equal Contribution