We propose a new stochastic gradient method that uses recorded past loss...
We introduce MADGRAD, a novel optimization method in the family of AdaGr...
First-order stochastic optimization methods are currently the most widel...
Momentum methods are now used pervasively within the machine learning
co...
We provide a comprehensive analysis of the Stochastic Heavy Ball (SHB) m...
The convergence rates for convex and non-convex optimization methods dep...
The slow acquisition speed of magnetic resonance imaging (MRI) has led t...
MRI images reconstructed from sub-sampled data using deep learning techn...
Purpose: To advance research in the field of machine learning for MR ima...
Deep learning approaches to accelerated MRI take a matrix of sampled
Fou...
Magnetic Resonance Image (MRI) acquisition is an inherently slow process...
In this work, we describe a set of rules for the design and initializati...
One representation of possible errors in a grayscale image reconstructio...
In this work we propose a differential geometric motivation for Nesterov...
We introduce a new normalization technique that exhibits the fast conver...
The application of stochastic variance reduction to optimization has sho...
Accelerating Magnetic Resonance Imaging (MRI) by taking fewer measuremen...
We describe a novel optimization method for finite sums (such as empiric...
A thesis submitted for the degree of Doctor of Philosophy of The Austral...
We apply stochastic average gradient (SAG) algorithms for training
condi...
Reinforcement learning agents have traditionally been evaluated on small...
In this work we introduce a new optimisation method called SAGA in the s...