Work

Continual Learning with Quasi-Newton Methods

Year: 2021

Type: preprint

Abstract: In this paper, we propose CSQN, a new Continual Learning (CL) method which considers Quasi-Newton methods, more specifically, Sampled Quasi-Newton methods, to extend EWC. EWC uses a Bayesian framework to estimate which parameters are important to previous tasks, and it punishes changes made to these parameters. However, it assumes that parameters are independent, as it does not consider interactions between parameters. With CSQN, we aim to overcome this.

DOI: 10.36227/techrxiv.16676701.v1

Authors: Steven Vander Eeckt, Hugo Van hamme

Institution: KU Leuven

Language: English

Topic: Domain Adaptation and Few-Shot Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W4244976296

Cites: 47

Cited by:

Related to: 10