91 citations · 113 across the 41 of their papers we have counts for
5 papers · 1 filter
A Damped Newton Method Achieves Global and Local Quadratic Convergence Rate
Slavomír Hanzely, Dmitry Kamzolov, Dmitry Pasechnyuk +3
In this paper, we present the first stepsize schedule for Newton method resulting in fast global and local convergence guarantees. In particular, a) we prove an $O\left( \frac 1 {k…
Effects of momentum scaling for SGD
Dmitry A. Pasechnyuk, Alexander Gasnikov, Martin Takáč
The paper studies the properties of stochastic gradient methods with preconditioning. We focus on momentum updated preconditioners with momentum coefficient . Seeking to explain…
Exploiting higher-order derivatives in convex optimization methods
Dmitry Kamzolov, Alexander Gasnikov, Pavel Dvurechensky +2
Exploiting higher-order derivatives in convex optimization is known at least since 1970's. In each iteration higher-order (also called tensor) methods minimize a regularized Taylor…
SP2: A Second Order Stochastic Polyak Method
Shuang Li, William J. Swartworth, Martin Takáč +2
Recently the "SP" (Stochastic Polyak step size) method has emerged as a competitive adaptive method for setting the step sizes of SGD. SP can be interpreted as a method specialized…
Suppressing Poisoning Attacks on Federated Learning for Medical Imaging
Naif Alkhunaizi, Dmitry Kamzolov, Martin Takáč +1
Collaboration among multiple data-owning entities (e.g., hospitals) can accelerate the training process and yield better machine learning models due to the availability and diversi…