activity
20182021
collaborators
Showing math.OCShow all

5 papers · 1 filter

math.OC2021

: A Fast sketching based solver for large scale ridge regression

Nidham Gazagnadou, Mark Ibrahim, Robert M. Gower

We propose new variants of the sketch-and-project method for solving large scale ridge regression problems. Firstly, we propose a new momentum alternative and provide a theorem sho…

math.OC2020

SGD for Structured Nonconvex Functions: Learning Rates, Minibatching and Interpolation

Robert M. Gower, Othmane Sebbouh, Nicolas Loizou

Stochastic Gradient Descent (SGD) is being used routinely for optimizing non-convex functions. Yet, the standard convergence theory for SGD in the smooth non-convex setting gives a…

math.OC2020

Fast Linear Convergence of Randomized BFGS

Dmitry Kovalev, Robert M. Gower, Peter Richtárik +1

Since the late 1950's when quasi-Newton methods first appeared, they have become one of the most widely used and efficient algorithmic paradigms for unconstrained optimization. Des…

math.OC2019

RSN: Randomized Subspace Newton

Robert M. Gower, Dmitry Kovalev, Felix Lieder +1

We develop a randomized Newton method capable of solving learning problems with huge dimensional feature spaces, which is a common setting in applications such as medical imaging,…

math.OC2018

Improving SAGA via a Probabilistic Interpolation with Gradient Descent

Adel Bibi, Alibek Sailanbayev, Bernard Ghanem +2

We develop and analyze a new algorithm for empirical risk minimization, which is the key paradigm for training supervised machine learning models. Our method---SAGD---is based on a…