Papers
arxiv:2405.13817

Thermodynamic Natural Gradient Descent

Published on May 22
ยท Submitted by akhaliq on May 24
Authors:
,
,
,
,

Abstract

Second-order training methods have better convergence properties than gradient descent but are rarely used in practice for large-scale training due to their computational overhead. This can be viewed as a hardware limitation (imposed by digital computers). Here we show that natural gradient descent (NGD), a second-order method, can have a similar computational complexity per iteration to a first-order method, when employing appropriate hardware. We present a new hybrid digital-analog algorithm for training neural networks that is equivalent to NGD in a certain parameter regime but avoids prohibitively costly linear system solves. Our algorithm exploits the thermodynamic properties of an analog system at equilibrium, and hence requires an analog thermodynamic computer. The training occurs in a hybrid digital-analog loop, where the gradient and Fisher information matrix (or any other positive semi-definite curvature matrix) are calculated at given time intervals while the analog dynamics take place. We numerically demonstrate the superiority of this approach over state-of-the-art digital first- and second-order training methods on classification tasks and language model fine-tuning tasks.

Community

Unlocking Neural Network Efficiency: Thermodynamic Natural Gradient Descent Explained

Links ๐Ÿ”—:

๐Ÿ‘‰ Subscribe: https://www.youtube.com/@Arxflix
๐Ÿ‘‰ Twitter: https://x.com/arxflix
๐Ÿ‘‰ LMNT (Partner): https://lmnt.com/

By Arxflix
9t4iCUHx_400x400-1.jpg

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2405.13817 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2405.13817 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2405.13817 in a Space README.md to link it from this page.

Collections including this paper 2