About

I am a final year PhD candidate in the Department of Computer Science at the University of Toronto, where I am advised by Dan Roy. I am also affiliated with the Vector Institute. I hold a Master’s degree in Computer Science, and a Bachelor’s degree in Electrical Engineering from the University of Toronto.

I primarily work in deep learning, although I have broad interests, spanning methodology (algorithms) and theory for machine learning. My current research exploits the geometric properties of deep neural network loss landscapes to design novel algorithms that enable parsimonious machine learning. My aim is to develop methods that are both time-efficient and resource-conscious, thereby democratizing machine learning by making it more accessible and deployable in diverse settings.

Previously, I explored problems in probabilistic programming, Bayesian nonparametrics, and computational biology.

I am on the job market for industry research positions! Check out my CV and reach out if you have an opening.

Research papers

Sparse Training from Random Initialization: Aligning Lottery Ticket Masks using Weight Symmetry
Rohan Jain, Mohammed Adnan, Ekansh Sharma, Yani Ioannou
ICML 2025
Links: [openreview]

The Non-Local Model Merging Problem: Permutation Symmetries and Variance Collapse
Ekansh Sharma, Daniel M. Roy, Gintare Karolina Dziugaite
preprint arXiv:2410.12766 (submitted for peer review) **
Links: [arXiv]

Simultaneous Linear Connectivity of Neural Networks Modulo Permutation
Ekansh Sharma, Devin Kwok, Tom Denton, Daniel M. Roy, David Rolnick , Gintare Karolina Dziugaite
ECML PKDD 2024 [doi]
Links: [paper][arXiv]

Bootstrap estimators for the tail-index and for the count statistics of graphex processes
Zacharie Naulet, Daniel M. Roy, Ekansh Sharma, Victor Veitch
Electronic Journal of Statistics, 15 (1) 282 - 325 2021 [doi]
Links: [paper][arXiv]

Approximations in Probabilistic Programs
Ekansh Sharma, Daniel M. Roy
PROBPROG 2020
Links: [arXiv][talk][poster]

Exchangeable modelling of relational data: checking sparsity, train-test splitting, and sparse exchangeable Poisson matrix factorization
Victor Veitch, Ekansh Sharma, Zacharie Naulet, Daniel M. Roy
preprint arXiv:1712.02311 2020
Links: [arXiv]

Contact

Email: ekansh -at- cs -dot- toronto -dot- edu
GitHub: https://github.com/ekanshs/
Office: Vector Institute
Schwartz Reisman Innovation Campus
108 College St W1140, Toronto, ON M5G 0C6