Vedant Shah

I am a Research Master's student at Mila and Université de Montréal where I am supervised by Prof. Yoshua Bengio's and Dr. Anirudh Goyal.

I completed my undergraduate studies in Electronics and Communications Engineering from BITS Pilani, Goa Campus where I was advised by Prof. Ashwin Srinivasan and Prof. Tanmay Verlekar at APPCAIR. I also spent a summer interning with Dr. Gautam Shroff at TCS Research and was selected for Google Summer of Code 2021.

At BITS, I was the Vice President of the Society for Artificial Intelligence and Deep Learning and Teaching Head of the Electronics and Robotics Club, BITS Goa.

Email  /  CV  /  Scholar  /  LinkedIn  /  Twitter  /  Github

profile photo
Recent News

Broadly, I am interested in improving the sample efficiency and out of distribution generalization abilities of Reinforcement Learning and Deep Learning agents. To this end, I am interested in looking into approaches based on human cognitive inductive biases, meta learning and neurosymbolic methods. Recently, I have been working on investigating different pretraining approaches for Deep Reinforcement Learning. I have also been working on using probabilistic inference framework of GFlowNet for Drug Discovery.

Unlearning via Sparse Representations
Vedant Shah, Frederik Träuble, Ashish Malik, Hugo Larochelle, Michael Mozer, Sanjeev Arora, Yoshua Bengio, Anirudh Goyal,

We propose a nearly compute-free approach for class unlearning in multi-class classification settings.

Stateful Active Facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning
Dianbo Liu*, Vedant Shah*, Oussama Boussif*, Cristian Meo, Anirudh Goyal, Tianmin Shu, Michael Mozer, Nicolas Heess, Yoshua Bengio,
ICLR 2023
arXiv / Talk

Investigating the problem of environmental heterogeneity and using behvioural priors to tackle the problems of coordination and heterogeneity in MARL

Neural Feature-Adaptation for Symbolic Predictions Using Pre-Training and Semantic Loss
Vedant Shah*, Aditya Agarwal*, Lovekesh Vig, Ashwin Srinivasan, Gautam Shroff, Tanmay Verlekar,

Using corrupted pretraining and semantic loss for obtaining explainable predictions in terms of human intelligible concepts by composing a symbolic and a neural module together.

Forecasting Market Prices using DL with Data Augmentation and Meta-learning: ARIMA still wins!
Vedant Shah, Gautam Shroff
I (Still) Can't Believe It's Not Better! Workshop, NeurIPS 2021
arXiv / Poster

We train state of the art deep learning models on financial data using a data augmentation with synthetic data and meta learning.
ARIMA still beats the deep learning models in forecasting market data.

Adapting Deep Neural Networks for Pedestrian-Detection to Low-Light Conditions without Re-training
Vedant Shah, Anmol Agarwal Tanmay Tulsidas Verlekar Raghavendra Singh
Workshop on Traditional Computer Vision in the Age of Deep Learning, ICCV 2021
PDF / Slides

We develop a real time pre-processing pipeline for helping deep neural networks in pedestrian detection in low-light conditions.

Sep 2023 - Present
Graduate Student Researcher
Advisor - Dr. Anirudh Goyal and Prof. Yoshua Bengio

Sep 2021 - July 2023
Research Intern
Advisors - Dr. Anirudh Goyal and Prof. Yoshua Bengio
Jan 2022 - Aug 2022
Undergraduate Researcher
Advisor - Prof. Ashwin Srinivasan

Jan 2021 - Aug 2021
Undergraduate Researcher
Advisor - Prof. Tanmay Verlekar
May 2021 - Sep 2021
Research Intern
Advisor - Dr. Gautam Shroff
May 2021 - Aug 2021
Student Developer
Organisation - GFOSS (Suborganisation - OpenDR)
Aug. 2020 - Nov. 2020
Research Intern
Advisor - Prof. GC Nandi

Original Templates: 1,2