I am a master’s student in the Department of Computer Science at the University of British Columbia, where I am advised by Mark Schmidt. My research interests are in optimization for machine learning.
June 15: New preprint is on arXiv! I had great fun helping out with the experiments for this work on implicit regularization and (effective) preconditioners in generalized linear models.
April 29: I will attend the (virtual) MLSS 2020 from 28 June to 10 July this summer.
September 25: I'm organizing UBC MLRG this year! The topic is generalization of neural networks; it will include "sharp" local minima, implicit reguarlization, and interpolation.
September 4: I was ranked in the top 50% of reviewers for NeurIPS 2019! This was my first time reviewing; I reviewed eight papers, including two emergency reviews.
September 4: Our work on stochastic line-searches has been accepted for a poster at NeurIPS 2019!
May 24: New work on line-searches for stochastic gradient descent (with convergence rates under interpolation) is on arXiv!
September 4: Our paper on low-rank Gaussian variational inference for Bayesian neural networks was accepted at NeurIPS 2018! The paper is available on arXiv here.
January 21 - June 30: I joined Emtiyaz Khan as an intern at the RIKEN Center for Advanced Intelligence Project (AIP).
To Each Optimizer a Norm, To Each Norm its Generalization. S. Vaswani, R. Babanezhad, J. Gallego, A. Mishkin, S. Lacoste-Julien, N. Le Roux. arXiv Preprint, 2020.
Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates. S. Vaswani, A. Mishkin, I. Laradji, M. Schmidt, G. Gidel, S. Lacoste-Julien. NeurIPS, 2019.
SLANG: Fast Structured Covariance Approximations for Bayesian Deep Learning with Natural Gradient. A. Mishkin, F. Kunstner, D. Nielsen, M. Schmidt, M. E. Khan. NeurIPS, 2018.
Web ValueCharts: Analyzing Individual and Group Preferences with Interactive, Web-based Visualizations. A. Mishkin. Review of Undergraduate Computer Science, 2018.