About

I am a Machine Learning Engineer at Google. I recently completed my PhD in the Department of Computer Science at the University of Toronto, where I was advised by Dan Roy and affiliated with the Vector Institute. I also hold a Master’s degree in Computer Science and a Bachelor’s degree in Electrical Engineering from the University of Toronto.

My research interests are primarily in deep learning, spanning methodology (algorithms) and theory for machine learning. I currently work on recommender systems for YouTube, developing LLMs and studying scaling laws for recommender systems. During my PhD, I exploited the geometric properties of deep neural network loss landscapes to design novel algorithms that enable parsimonious machine learning—methods that are both time-efficient and resource-conscious, making machine learning more accessible and deployable in diverse settings.

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

Research papers

SparseOpt: Addressing Normalization-induced Gradient Skew in Sparse Training
Mohammed Adnan, Rohan Jain, Tom Jacobs, Ekansh Sharma, Rahul G. Krishnan, Rebekka Burkholz, Yani Ioannou
ICML 2026
Links: [arXiv]

TokenMinds: Pretrained User Tokens and Embeddings for User Understanding in Large Recommender Systems
Qingyun Liu, Bo Yan, Yang Liu, Yuji Roh, Ekansh Sharma, Likang Yin, Emma Olowo, Min-Hsuan Tsai, Yuxuan Li, Diego Uribe, Saksham Aggarwal, Siqi Wu, Yuan Hao, Vikas Kedigehalli, Lukasz Heldt, Lichan Hong, Li Wei, Xinyang Yi
preprint arXiv:2606.25147 (submitted for peer review)
Links: [arXiv]

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