Karush Suri
Hi! I am a research engineer at Google X in Mountain View. Previously, I was a student researcher at Borealis AI. I completed my M.A.Sc in Computer Engineering at the University of Toronto with Yuri Lawryshyn and Kostas Plataniotis. My work was supported by the Edward S. Rogers Graduate Scholarship and ECE Fellowships. I earned my B.Tech in Electrical Engineering and Applied Mathematics from Amity University where I was affiliated as an undergraduate research assistant with Rinki Gupta. My work was a recipient of the Best Undergraduate Thesis Award. Besides research, I enjoy reading comic books and novels.
I aim to create generalist agents capable of accelerating their own learning. These agents must reason about sequential patterns and structures across a broad range of environments. Towards this goal, I develop algorithms in Meta Learning, Reinforcement Learning and Graph Representation Learning for addressing real-world sequence modelling problems.
Publications
Surprise Minimizing Multi-Agent Learning with Energy-based Models
K Suri, X Q Shi, K Plataniotis, Y Lawryshyn
NeurIPS 2022
paper webpage code talk reviews
Off-Policy Evolutionary Reinforcement Learning with Maximum Mutations
K Suri
AAMAS 2022. (oral)
paper webpage code blog talk reviews
Continuous Sign Language Recognition from Wearable IMUs using CapsNet and Game Theory
K Suri, R Gupta
Computers And Electrical Engineering, Elsevier, Vol. 78, 2019.
paper code demo reviews
Transfer Learning for sEMG-based Hand Gesture Classification using Master-Slave Nets
K Suri, R Gupta
IEEE IC3I 2018.
paper
Theses
Deep Hierarchical Reinforcement Learning
K Suri
University of Toronto, M.A.Sc Thesis, 2021.
link
Deep Learning and Game Theory for Wearable Sensors
K Suri
Amity University, B.Tech Thesis, 2019.
link demo
Blog Posts
Discrete Stochastic Optimization
2024.
link
Data Parallelism in JAX
2024.
link
Coarsening Graphs with Neural Networks
ICLR 2022 Blog Track
2021.
link reviews
Variational Generalization Bounds
2020.
link
Evolution-based Soft Actor-Critic
2020.
link
Stacked Capsule Autoencoders
2020.
link
Benchmarking Policy Search using Cyclic MDP
2019.
link
DQN with Atari in 6 Minutes
2019.
link
Capsule Networks for Digit Recognition in PyTorch
2018.
link