Alexander Shestakov

Loss Transformation Invariance of the Damped Newton Methods

Johnson-Lindenstrauss Transforms in Distributed Optimization

Why SGD is not Brownian Motion: A New Perspective on Stochastic Dynamics

Unified Theory of Adaptive Variance Reduction

Dynamic Compression in Distributed Communications for Reduction of Transmission Losses

Diminishing Noise Maintains Differential Privacy and Enhances Convergence

Adaptive Regularized Newton Methods with Inexact Hessian