Sai Srivatsa
Ravindranath

sai
harvard

I am a first year PhD student in Computer Science at Harvard university, where I am a part of the EconCS Group. I’m currently working with Prof. David Parkes on Machine Learning for economic systems and multi-agent system design.

Before coming to Harvard, I was a Research Fellow at the Machine Learning and Optimization group, Microsoft Research, India working with Dr. Prateek Jain on large-scale multi-label learning. I completed my undergraduate studies at Indian Institute of Technology, Kharagpur. I did my undergraduate internships at Computer Vision Lab, ETH Zurich under the supervision of Prof. Luc Van Gool and also at the Video Analytics Lab at CDS, IISc Bangalore


Email  |  CV  |  Google Scholar  |  Github


Publications

From Predictions to Decisions: Using Lookahead Regularization
N. Rosenfeld, S. Hilgard, SS. Ravindranath, DC. Parkes
Neural Information Processing Systems (NeurIPS), 2020
[Paper] [Code]

Optimal Auctions through Deep Learning*
P. Dutting, Z. Feng, H. Narasimhan, DC Parkes, SS. Ravindranath
International Conference on Machine Learning (ICML), 2019
*Authors ordered alphabetically, Accepted as Long Oral
[Paper] [Code]

Learning Objective functions for Improved Image retrieval
SS. Ravindranath, M. Gygli, LV. Gool
MediaEval 2015 Workshops
[Paper]

Salient Object Detection via Objectness Measure
SS. Ravindranath , RV. Babu
International Conference on Image Processing (ICIP), 2015
[Project] [Paper] [Poster] [Code]


Book Chapters

Machine Learning for Optimal Economic Design
P. Dutting, Z. Feng, N. Golowich, H. Narasimhan, DC. Parkes, SS. Ravindranath
In JF Laslier, H. Moulin, MR. Sanver, WS. Zwicker, editors,
The Future of Economic Design. Springer, 2019


Press Coverage

IIT Kharagpur innovation to monitor fatigue level in pilots.
Hindustan Times, 2016

Stressed? Now, wear a pair of glasses and find out how much.
Times of India, 2016


Code

Lookahead Regularization [Code]

Optimal Auctions through Deep Learning [Code]

Salient Object Detection via Objectness Measure [Code]