2021-07-01-alvarez-melis21a.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
Dataset Dynamics via Gradient Flows in Probability Space	Various machine learning tasks, from generative modeling to domain adaptation, revolve around the concept of dataset transformation and manipulation. While various methods exist for transforming unlabeled datasets, principled methods to do so for labeled (e.g., classification) datasets are missing. In this work, we propose a novel framework for dataset transformation, which we cast as optimization over data-generating joint probability distributions. We approach this class of problems through Wasserstein gradient flows in probability space, and derive practical and efficient particle-based methods for a flexible but well-behaved class of objective functions. Through various experiments, we show that this framework can be used to impose constraints on classification datasets, adapt them for transfer learning, or to re-purpose fixed or black-box models to classify {—}with high accuracy{—} previously unseen datasets.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	alvarez-melis21a	0	Dataset Dynamics via Gradient Flows in Probability Space	219	230	219-230	219	false	Alvarez-Melis, David and Fusi, Nicol\`o	given family David Alvarez-Melis given family Nicolò Fusi	2021-07-01		Proceedings of the 38th International Conference on Machine Learning	139	inproceedings	date-parts 2021 7 1	http://proceedings.mlr.press/v139/alvarez-melis21a/alvarez-melis21a.pdf	label link Supplementary PDF http://proceedings.mlr.press/v139/alvarez-melis21a/alvarez-melis21a-supp.pdf