Stochastic Linear Contextual Bandits with Diverse Contexts

March 05, 2020 ยท Declared Dead ยท ๐Ÿ› International Conference on Artificial Intelligence and Statistics

๐Ÿ‘ป CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Weiqiang Wu, Jing Yang, Cong Shen arXiv ID 2003.02681 Category cs.LG: Machine Learning Cross-listed cs.IT, stat.ML Citations 14 Venue International Conference on Artificial Intelligence and Statistics Last Checked 5 months ago
Abstract
In this paper, we investigate the impact of context diversity on stochastic linear contextual bandits. As opposed to the previous view that contexts lead to more difficult bandit learning, we show that when the contexts are sufficiently diverse, the learner is able to utilize the information obtained during exploitation to shorten the exploration process, thus achieving reduced regret. We design the LinUCB-d algorithm, and propose a novel approach to analyze its regret performance. The main theoretical result is that under the diverse context assumption, the cumulative expected regret of LinUCB-d is bounded by a constant. As a by-product, our results improve the previous understanding of LinUCB and strengthen its performance guarantee.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning

Died the same way โ€” ๐Ÿ‘ป Ghosted