Konstantin Mishchenko

activity

20182023

most citedStochastic Distributed Learning with Gradient Quantization and Variance Reduction

81 citations · 147 across the 20 of their papers we have counts for

collaborators

Showing 2021 · math.OCShow all

2 papers · 2 filters

math.OC2021★ 5 cited

Regularized Newton Method with Global $O (1/ k^{2})$ Convergence

Konstantin Mishchenko

We present a Newton-type method that converges fast from any initialization and for arbitrary convex objectives with Lipschitz Hessians. We achieve this by merging the ideas of cub…

math.OC2021

On Seven Fundamental Optimization Challenges in Machine Learning

Konstantin Mishchenko

Many recent successes of machine learning went hand in hand with advances in optimization. The exchange of ideas between these fields has worked both ways, with machine learning bu…

Regularized Newton Method with Global O(1/k2) Convergence

On Seven Fundamental Optimization Challenges in Machine Learning

Regularized Newton Method with Global $O (1/ k^{2})$ Convergence