3 papers
cs.LG2020
Variance-Reduced Methods for Machine Learning
Robert M. Gower, Mark Schmidt, Francis Bach +1
Stochastic optimization lies at the heart of machine learning, and its cornerstone is stochastic gradient descent (SGD), a method introduced over 60 years ago. The last 8 years hav…
math.NA2019
Adaptive Sketch-and-Project Methods for Solving Linear Systems
Robert Gower, Denali Molitor, Jacob Moorman +1
We present new adaptive sampling rules for the sketch-and-project method for solving linear systems. To deduce our new sampling rules, we first show how the progress of one step of…
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,…