2022-11-28-li22a.md

title	abstract	video	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Energy-Based Models for Continual Learning	We motivate Energy-Based Models (EBMs) as a promising model class for continual learning problems. Instead of tackling continual learning via the use of external memory, growing models, or regularization, EBMs change the underlying training objective to cause less interference with previously learned information. Our proposed version of EBMs for continual learning is simple, efficient, and outperforms baseline methods by a large margin on several benchmarks. Moreover, our proposed contrastive divergence-based training objective can be combined with other continual learning methods, resulting in substantial boosts in their performance. We further show that EBMs are adaptable to a more general continual learning setting where the data distribution changes without the notion of explicitly delineated tasks. These observations point towards EBMs as a useful building block for future continual learning methods.	https://youtu.be/iZ4cz5RQmzE	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	li22a	0	Energy-Based Models for Continual Learning	1	22	1-22	1	false	Li, Shuang and Du, Yilun and van de Ven, Gido and Mordatch, Igor	given family Shuang Li given family Yilun Du given family prefix Gido Ven van de given family Igor Mordatch	2022-11-28		Proceedings of The 1st Conference on Lifelong Learning Agents	199	inproceedings	date-parts 2022 11 28	https://proceedings.mlr.press/v199/li22a/li22a.pdf