Search Results for author: David Hyde

Found 2 papers, 0 papers with code

A Deep Gradient Correction Method for Iteratively Solving Linear Systems

no code implementations22 May 2022 Ayano Kaneda, Osman Akar, Jingyu Chen, Victoria Kala, David Hyde, Joseph Teran

We present a novel deep learning approach to approximate the solution of large, sparse, symmetric, positive-definite linear systems of equations.

Improved Search Strategies with Application to Estimating Facial Blendshape Parameters

no code implementations7 Dec 2018 Michael Bao, David Hyde, Xinru Hua, Ronald Fedkiw

It is well known that popular optimization techniques can lead to overfitting or even a lack of convergence altogether; thus, practitioners often utilize ad hoc regularization terms added to the energy functional.

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