research
∙
01/31/2022
Memory-Efficient Backpropagation through Large Linear Layers
In modern neural networks like Transformers, linear layers require signi...
share
research
∙
03/15/2021
Meta-Solver for Neural Ordinary Differential Equations
A conventional approach to train neural ordinary differential equations ...
research
∙
07/14/2020
Follow the bisector: a simple method for multi-objective optimization
This study presents a novel Equiangular Direction Method (EDM) to solve ...
research
∙
04/20/2020
Towards Understanding Normalization in Neural ODEs
Normalization is an important and vastly investigated technique in deep ...
research
∙
03/11/2020
Interpolated Adjoint Method for Neural ODEs
In this paper, we propose a method, which allows us to alleviate or comp...
research
∙
09/28/2019
Practical shift choice in the shift-and-invert Krylov subspace evaluations of the matrix exponential
We propose two methods to find a proper shift parameter in the shift-and...
research
∙
03/05/2019