2021-07-21-hsu21a.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
On the Approximation Power of Two-Layer Networks of Random ReLUs	This paper considers the following question: how well can depth-two ReLU networks with randomly initialized bottom-level weights represent smooth functions? We give near-matching upper- and lower-bounds for L2-approximation in terms of the Lipschitz constant, the desired accuracy, and the dimension of the problem, as well as similar results in terms of Sobolev norms. Our positive results employ tools from harmonic analysis and ridgelet representation theory, while our lower-bounds are based on (robust versions of) dimensionality arguments.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	hsu21a	0	On the Approximation Power of Two-Layer Networks of Random ReLUs	2423	2461	2423-2461	2423	false	Hsu, Daniel and Sanford, Clayton H and Servedio, Rocco and Vlatakis-Gkaragkounis, Emmanouil Vasileios	given family Daniel Hsu given family Clayton H Sanford given family Rocco Servedio given family Emmanouil Vasileios Vlatakis-Gkaragkounis	2021-07-21		Proceedings of Thirty Fourth Conference on Learning Theory	134	inproceedings	date-parts 2021 7 21	http://proceedings.mlr.press/v134/hsu21a/hsu21a.pdf