2024-06-30-fokkema24a.md

title	section	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
Online Newton Method for Bandit Convex Optimisation Extended Abstract	Original Papers	We introduce a computationally efficient algorithm for zeroth-order bandit convex optimisation and prove that in the adversarial setting its regret is at most $d^{3.5} \sqrt{n} \mathrm{polylog}(n, d)$ with high probability where $d$ is the dimension and $n$ is the time horizon. In the stochastic setting the bound improves to $M d^{2} \sqrt{n} \mathrm{polylog}(n, d)$ where $M \in [d^{-1/2}, d^{-1/4}]$ is a constant that depends on the geometry of the constraint set and the desired computational properties.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	fokkema24a	0	Online Newton Method for Bandit Convex Optimisation Extended Abstract	1713	1714	1713-1714	1713	false	Fokkema, Hidde and Van der Hoeven, Dirk and Lattimore, Tor and J. Mayo, Jack	given family Hidde Fokkema given family prefix Dirk Hoeven Van der given family Tor Lattimore given family Jack J. Mayo	2024-06-30		Proceedings of Thirty Seventh Conference on Learning Theory	247	inproceedings	date-parts 2024 6 30	https://proceedings.mlr.press/v247/fokkema24a/fokkema24a.pdf