2023-04-11-awasthi23b.md

title	software	abstract	section	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
Theory and Algorithm for Batch Distribution Drift Problems	https://github.com/chrismohrii/Drift_AISTATS	We study a problem of batch distribution drift motivated by several applications, which consists of determining an accurate predictor for a target time segment, for which a moderate amount of labeled samples are at one’s disposal, while leveraging past segments for which substantially more labeled samples are available. We give new algorithms for this problem guided by a new theoretical analysis and generalization bounds derived for this scenario. We further extend our results to the case where few or no labeled data is available for the period of interest. Finally, we report the results of extensive experiments demonstrating the benefits of our drifting algorithm, including comparisons with natural baselines. A by-product of our study is a principled solution to the problem of multiple-source adaptation with labeled source data and a moderate amount of target labeled data, which we briefly discuss and compare with.	Regular Papers	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	awasthi23b	0	Theory and Algorithm for Batch Distribution Drift Problems	9826	9851	9826-9851	9826	false	Awasthi, Pranjal and Cortes, Corinna and Mohri, Christopher	given family Pranjal Awasthi given family Corinna Cortes given family Christopher Mohri	2023-04-11		Proceedings of The 26th International Conference on Artificial Intelligence and Statistics	206	inproceedings	date-parts 2023 4 11	https://proceedings.mlr.press/v206/awasthi23b/awasthi23b.pdf