2023-04-11-baek23a.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
TS-UCB: Improving on Thompson Sampling With Little to No Additional Computation	https://github.com/jwbaek/TS-UCB-Code	Thompson sampling has become a ubiquitous approach to online decision problems with bandit feedback. The key algorithmic task for Thompson sampling is drawing a sample from the posterior of the optimal action. We propose an alternative arm selection rule we dub TS-UCB, that requires negligible additional computational effort but provides significant performance improvements relative to Thompson sampling. At each step, TS-UCB computes a score for each arm using two ingredients: posterior sample(s) and upper confidence bounds. TS-UCB can be used in any setting where these two quantities are available, and it is flexible in the number of posterior samples it takes as input. TS-UCB achieves materially lower regret on a comprehensive suite of synthetic and real-world datasets, including a personalized article recommendation dataset from Yahoo! and a suite of benchmark datasets from a deep bandit suite proposed in Riquelme et al. (2018). Finally, from a theoretical perspective, we establish optimal regret guarantees for TS-UCB for both the K-armed and linear bandit models.	Regular Papers	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	baek23a	0	TS-UCB: Improving on Thompson Sampling With Little to No Additional Computation	11132	11148	11132-11148	11132	false	Baek, Jackie and Farias, Vivek	given family Jackie Baek given family Vivek Farias	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/baek23a/baek23a.pdf