Papers
arxiv:2502.11756

On the Computation of the Fisher Information in Continual Learning

Published on Feb 17
Authors:

Abstract

The blog post examines different implementations of Fisher Information computation in Elastic Weight Consolidation (EWC) for continual learning, suggesting potential improvements in reported results.

AI-generated summary

One of the most popular methods for continual learning with deep neural networks is Elastic Weight Consolidation (EWC), which involves computing the Fisher Information. The exact way in which the Fisher Information is computed is however rarely described, and multiple different implementations for it can be found online. This blog post discusses and empirically compares several often-used implementations, which highlights that many currently reported results for EWC could likely be improved by changing the way the Fisher Information is computed.

Community

Sign up or log in to comment

Models citing this paper 1

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2502.11756 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/2502.11756 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.