2022-06-28-boursier22a.md

title	abstract	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
Trace norm regularization for multi-task learning with scarce data	Multi-task learning leverages structural similarities between multiple tasks to learn despite very few samples. Motivated by the recent success of neural networks applied to data-scarce tasks, we consider a linear low-dimensional shared representation model. Despite an extensive literature, existing theoretical results either guarantee weak estimation rates or require a large number of samples per task. This work provides the first estimation error bound for the trace norm regularized estimator when the number of samples per task is small. The advantages of trace norm regularization for learning data-scarce tasks extend to meta-learning and are confirmed empirically on synthetic datasets.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	boursier22a	0	Trace norm regularization for multi-task learning with scarce data	1303	1327	1303-1327	1303	false	Boursier, Etienne and Konobeev, Mikhail and Flammarion, Nicolas	given family Etienne Boursier given family Mikhail Konobeev given family Nicolas Flammarion	2022-06-28		Proceedings of Thirty Fifth Conference on Learning Theory	178	inproceedings	date-parts 2022 6 28	https://proceedings.mlr.press/v178/boursier22a/boursier22a.pdf	label link Supplementary ZIP https://proceedings.mlr.press/v178/boursier22a/boursier22a-supp.zip