Igor E. Preobrazhenskii

collaborators

2 papers

math.OC2026

Last Iterate Convergence of AdaGrad-Norm for Convex Non-Smooth Optimization

Margarita Preobrazhenskaia, Makar Sidorov, Igor Preobrazhenskii +1

We study the convergence of the last iterate (i.e., the $(N + 1)$ -th iterate) of the AdaGrad method. Although AdaGrad -- an adaptive subgradient method -- underpins a wide class of a…

math.DS2024

A cycle with a "short" period in the phenomenological model of a single neuron

Margarita M. Preobrazhenskaia, Igor E. Preobrazhenskii

We consider the relay version of the generalized Hutchinson's equation as a phenomenological model of an isolated neuron. After an exponential substitution, the equation takes the…