©2019 by Sam Sinha. Proudly created with Wix.com

SAMARTH SINHA

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

I am currently at  MILA as a visiting student with Anirudh Goyal, Hugo Larochelle and Yoshua Bengio

I am a fourth year undergraduate student in Computer Engineering at the University of Toronto where I work with Animesh Garg and Roger Grosse. Previously, I was a visiting student at UC Berkeley, working with Trevor Darrell and Zeynep Akata; before I worked with Ozan Sener as a part of CVGL at Stanford University. 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. 

IMG_4728.JPG
 
0_SfyW9nJXB1Omx8_s.png

RESEARCH INTERESTS

My research interests span across Deep Learning and Reinforcement Learning. I am interested in training models that can learn with minimal supervision, while generalizing beyond the test set.  

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

 

PUBLICATIONS / PRE-PRINTS

CONSISTENCY REGULARIZATION FOR VARIATIONAL AUTOENCODERS

Samarth Sinha, Augustus Odena, Adji Dieng (2020)

In review, arXiv soon

DIVA: DIVERSE VISUAL FEATURE AGGREGATION FOR DEEP METRIC LEARNING

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

In review, arXiv soon

CURRICULUM BY TEXTURE

Samarth Sinha, Animesh Garg, Hugo Larochelle (2020)

arXiv

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

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

arXiv

EXPERIENCE REPLAY WITH LIKELIHOOD-FREE IMPORTANCE WEIGHTS

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

In review, arXiv soon

REVISITING TRAINING STRATEGIES AND GENERALIZATION PERFORMANCE IN DEEP METRIC LEARNING

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

arXiv

DIBS: DIVERSITY INDUCING INFORMATION BOTTLENECK IN MODEL ENSEMBLES

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

arXiv

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

arXiv

Samarth Sinha*, Sayna Ebrahimi*, Trevor Darrell

ICCV 2019 (Oral)

Edgar Schönfeld, Sayna Ebrahimi, Samarth SinhaTrevor Darrell, Zeynep Akata 

CVPR 2019, ICLR LLD Workshop 2019