Search Results for author: Cameron Wolfe

Found 3 papers, 1 papers with code

REX: Revisiting Budgeted Training with an Improved Schedule

no code implementations9 Jul 2021 John Chen, Cameron Wolfe, Anastasios Kyrillidis

Deep learning practitioners often operate on a computational and monetary budget.

Momentum-inspired Low-Rank Coordinate Descent for Diagonally Constrained SDPs

no code implementations16 Jun 2021 Junhyung Lyle Kim, Jose Antonio Lara Benitez, Mohammad Taha Toghani, Cameron Wolfe, Zhiwei Zhang, Anastasios Kyrillidis

We present a novel, practical, and provable approach for solving diagonally constrained semi-definite programming (SDP) problems at scale using accelerated non-convex programming.

Demon: Improved Neural Network Training with Momentum Decay

2 code implementations11 Oct 2019 John Chen, Cameron Wolfe, Zhao Li, Anastasios Kyrillidis

Momentum is a widely used technique for gradient-based optimizers in deep learning.

Image Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.