4 papers
Why SGD is not Brownian Motion: A New Perspective on Stochastic Dynamics
Igor Ignashin, Anna Radovskaya, Andrew Semenov +7
Stochastic Gradient Descent (SGD) is commonly modeled as a Langevin process, assuming that minibatch noise acts as Brownian motion. However, this approximation relies on a continuo…
Modeling skiers flows via Wardrope equilibrium in closed capacitated networks
Demyan Yarmoshik, Igor Ignashin, Ekaterina Sikacheva +1
We propose an equilibrium model of ski resorts where users are assigned to cycles in a closed network. As queues form on lifts with limited capacity, we derive an efficient way to…
Stochastic Origin Frank-Wolfe for traffic assignment
Igor Ignashin, Demyan Yarmoshik, Andrei Raigorodskii
In this paper, we present the Stochastic Origin Frank-Wolfe (SOFW) method, which is a special case of the block-coordinate Frank-Wolfe algorithm, applied to the problem of finding…
Aligning Distributionally Robust Optimization with Practical Deep Learning Needs
Dmitrii Feoktistov, Igor Ignashin, Andrey Veprikov +4
While traditional Deep Learning (DL) optimization methods treat all training samples equally, Distributionally Robust Optimization (DRO) adaptively assigns importance weights to di…