SAMARTH SINHA

samarth [dot] sinha [at] mail [dot] utoronto [dot] ca

I am an undergraduate student in Computer Engineering at the University of Toronto and Vector Institute where I work with Animesh Garg and Roger Grosse on the intersection of machine learning and reinforcement learning.

 

Previously, I was a visiting student at MILA working closely with Anirudh Goyal, Hugo Larochelle and Yoshua Bengio; I was also a visitor at UC Berkeley, working with Trevor Darrell and Zeynep Akata. I have also been very fortunate to work at some amazing startups: Aurora, DeepMap, Concured, Nanoleaf

I spent my high school summers working with Alex Lvovsky working on Quantum Optics and with Guenther Ruhe working on Software Engineering at the University of Calgary. 

IMG_4728.JPG
 
0_SfyW9nJXB1Omx8_s.png

RESEARCH INTERESTS

My research interests span across Deep Learning and (Deep) Reinforcement Learning. I am interested in training models and agents that can learn generalizable representations from minimal supervision.

I have had the privilege to work with some amazing collaborators, and I am always interested in chatting about new problems. If you find anything interesting on the website, please get in touch!

 

PUBLICATIONS / PRE-PRINTS

Karsten Roth*, Timo Milbich*, Homanga Bharadhwaj, Samarth Sinha, Joseph Paul Cohen, Bjorn Ommer, Yoshua Bengio (2020)

ECCV 2020

CURRICULUM BY SMOOTHING

Samarth Sinha, Animesh Garg, Hugo Larochelle (2020)

arXiv

TOP-K TRAINING OF GANS: IMPROVING GAN PERFORMANCE BY THROWING AWAY BAD SAMPLES

Samarth Sinha*, Zhengli Zhao*, Anirudh Goyal, Colin Raffel, Augustus Odena (2020)

arXiv

EXPERIENCE REPLAY WITH LIKELIHOOD-FREE IMPORTANCE WEIGHTS

Samarth Sinha*, Jiaming Song*, Animesh Garg, Stefano Ermon (2020)

arXiv

Karsten Roth*, Timo Milbich*, Samarth Sinha, Prateek Gupta, Bjoern Ommer, Joseph Paul Cohen (2020)

ICML 2020 

DIBS: DIVERSITY INDUCING INFORMATION BOTTLENECK IN MODEL ENSEMBLES

Samarth Sinha*, Homanga Bharadhwaj*, Anirudh Goyal, Hugo Larochelle, Animesh Garg, Florian Shkurti (2020)

ICML-UDL Workshop 2020, arXiv

Samarth Sinha, Han Zhang, Anirudh Goyal, Yoshua Bengio, Hugo Larochelle, Augustus Odena (2019)

ICML 2020 

Samarth Sinha*, Sayna Ebrahimi*, Trevor Darrell (2019)

ICCV 2019 (Oral)

Edgar Schönfeld, Sayna Ebrahimi, Samarth SinhaTrevor Darrell, Zeynep Akata (2018)

CVPR 2019, ICLR LLD Workshop 2019

Samarth Sinha, Anirudh Goyal, Animesh Garg (2020)

arXiv