{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/variance-aware-linear-ucb-with-deep","title":"Variance-Aware Linear UCB with Deep Representation for Neural Contextual Bandits","arxiv_id":"2411.05979","date":"2024-11-08","proceeding":null,"authors":["Ha Manh Bui","Enrique Mallada","Anqi Liu"],"abstract":"By leveraging the representation power of deep neural networks, neural upper confidence bound (UCB) algorithms have shown success in contextual bandits. To further balance the exploration and exploitation, we propose Neural-$\\sigma^2$-LinearUCB, a variance-aware algorithm that utilizes $\\sigma^2_t$, i.e., an upper bound of the reward noise variance at round $t$, to enhance the uncertainty quantification quality of the UCB, resulting in a regret performance improvement. We provide an oracle version for our algorithm characterized by an oracle variance upper bound $\\sigma^2_t$ and a practical version with a novel estimation for this variance bound. Theoretically, we provide rigorous regret analysis for both versions and prove that our oracle algorithm achieves a better regret guarantee than other neural-UCB algorithms in the neural contextual bandits setting. Empirically, our practical method enjoys a similar computational efficiency, while outperforming state-of-the-art techniques by having a better calibration and lower regret across multiple standard settings, including on the synthetic, UCI, MNIST, and CIFAR-10 datasets.","url_abs":"https://arxiv.org/abs/2411.05979v1","url_pdf":"https://arxiv.org/pdf/2411.05979v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"variance-aware-linear-ucb-with-deep","repo_url":"https://github.com/angie-lab-jhu/neuralvarlinucb","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"multi-armed-bandits","task_name":"Multi-Armed Bandits"},{"task_slug":"uncertainty-quantification","task_name":"Uncertainty Quantification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.05979","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}