77 citations · 318 across the 57 of their papers we have counts for
3 papers · 1 filter
Aiming towards the minimizers: fast convergence of SGD for overparametrized problems
Chaoyue Liu, Dmitriy Drusvyatskiy, Mikhail Belkin +2
Modern machine learning paradigms, such as deep learning, occur in or close to the interpolation regime, wherein the number of model parameters is much larger than the number of da…
The slope robustly determines convex functions
Aris Daniilidis, Dmitriy Drusvyatskiy
We show that the deviation between the slopes of two convex functions controls the deviation between the functions themselves. This result reveals that the slope -- a one dimension…
Asymptotic normality and optimality in nonsmooth stochastic approximation
Damek Davis, Dmitriy Drusvyatskiy, Liwei Jiang
In their seminal work, Polyak and Juditsky showed that stochastic approximation algorithms for solving smooth equations enjoy a central limit theorem. Moreover, it has since been a…