3 citations · 3 across the 2 of their papers we have counts for
3 papers
math.OC2020★ 3 cited
Follow the bisector: a simple method for multi-objective optimization
Alexandr Katrutsa, Daniil Merkulov, Nurislam Tursynbek +1
This study presents a novel Equiangular Direction Method (EDM) to solve a multi-objective optimization problem. We consider optimization problems, where multiple differentiable los…
stat.ML2020
Stochastic gradient algorithms from ODE splitting perspective
Daniil Merkulov, Ivan Oseledets
We present a different view on stochastic optimization, which goes back to the splitting schemes for approximate solutions of ODE. In this work, we provide a connection between sto…
cs.LG2019
Empirical study of extreme overfitting points of neural networks
Daniil Merkulov, Ivan Oseledets
In this paper we propose a method of obtaining points of extreme overfitting - parameters of modern neural networks, at which they demonstrate close to 100 % training accuracy, sim…