activity
20192021
most citedLayered SGD: A Decentralized and Synchronous SGD Algorithm for Scalable Deep Neural Network Training

8 citations · 8 across the 3 of their papers we have counts for

collaborators

6 papers

math.OC2021

Stochastic Projective Splitting: Solving Saddle-Point Problems with Multiple Regularizers

Patrick R. Johnstone, Jonathan Eckstein, Thomas Flynn +1

We present a new, stochastic variant of the projective splitting (PS) family of algorithms for monotone inclusion problems. It can solve min-max and noncooperative game formulation…

math.OC2020

A persistent adjoint method with dynamic time-scaling and an application to mass action kinetics

Thomas Flynn

In this article we consider an optimization problem where the objective function is evaluated at the fixed-point of a contraction mapping parameterized by a control variable, and o…

math.OC2020

Bounding the expected run-time of nonconvex optimization with early stopping

Thomas Flynn, Kwang Min Yu, Abid Malik +2

This work examines the convergence of stochastic gradient-based optimization algorithms that use early stopping based on a validation function. The form of early stopping we consid…

cs.LG20198 cited

Layered SGD: A Decentralized and Synchronous SGD Algorithm for Scalable Deep Neural Network Training

Kwangmin Yu, Thomas Flynn, Shinjae Yoo +1

Stochastic Gradient Descent (SGD) is the most popular algorithm for training deep neural networks (DNNs). As larger networks and datasets cause longer training times, training on d…

math.OC2019

A Simultaneous Perturbation Weak Derivative Estimator for Stochastic Neural Networks

Thomas Flynn, Felisa Vázquez-Abad

In this paper we study gradient estimation for a network of nonlinear stochastic units known as the Little model. Many machine learning systems can be described as networks of homo…

math.ST2019

Change Detection with the Kernel Cumulative Sum Algorithm

Thomas Flynn, Shinjae Yoo

Online change detection involves monitoring a stream of data for changes in the statistical properties of incoming observations. A good change detector will detect any changes shor…