4 citations · 4 across the 10 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.LG2023
MAST: Model-Agnostic Sparsified Training
Yury Demidovich, Grigory Malinovsky, Egor Shulgin +1
We introduce a novel optimization problem formulation that departs from the conventional way of minimizing machine learning model loss as a black-box function. Unlike traditional f…
cs.LG2023★ 4 cited
A Guide Through the Zoo of Biased SGD
Yury Demidovich, Grigory Malinovsky, Igor Sokolov +1
Stochastic Gradient Descent (SGD) is arguably the most important single algorithm in modern machine learning. Although SGD with unbiased gradient estimators has been studied extens…