# Deep Upper Confidence Bound Algorithm for Contextual Bandit Ranking of Information Selection

arXiv: https://arxiv.org/abs/2110.04127 · HTML: https://mlsanity.com/paper/2110.04127/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 18 references that are in the map.
- First posted on arXiv 8 Oct 2021.

## Builds on (most cited first, 3 of 3)

- [Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson Sampling](https://mlsanity.com/paper/1802.09127/) (2018)
- [Deep Bayesian Bandits: Exploring in Online Personalized Recommendations](https://mlsanity.com/paper/2008.00727/) (2020)
- [Deep Neural Linear Bandits: Overcoming Catastrophic Forgetting through Likelihood Matching](https://mlsanity.com/paper/1901.08612/) (2019)

## Built on by (most cited first, 3 of 3)

- [Convergence Guarantees for Deep Epsilon Greedy Policy Learning](https://mlsanity.com/paper/2112.03376/) (2021)
- [Optimal Policy Learning with Observational Data in Multi-Action Scenarios: Estimation, Risk Preference, and Potential Failures](https://mlsanity.com/paper/2403.20250/) (2024)
- [Improving Reward-Conditioned Policies for Multi-Armed Bandits using Normalized Weight Functions](https://mlsanity.com/paper/2406.10795/) (2024)

## Abstract (arXiv)

Contextual multi-armed bandits (CMAB) have been widely used for learning to filter and prioritize information according to a user's interest. In this work, we analyze top-K ranking under the CMAB framework where the top-K arms are chosen iteratively to maximize a reward. The context, which represents a set of observable factors related to the user, is used to increase prediction accuracy compared to a standard multi-armed bandit. Contextual bandit methods have mostly been studied under strict linearity assumptions, but we drop that assumption and learn non-linear stochastic reward functions with deep neural networks. We introduce a novel algorithm called the Deep Upper Confidence Bound (UCB) algorithm. Deep UCB balances exploration and exploitation with a separate neural network to model the learning convergence. We compare the performance of many bandit algorithms varying K over real-world data sets with high-dimensional data and non-linear reward functions. Empirical results show that the performance of Deep UCB often outperforms though it is sensitive to the problem and reward setup. Additionally, we prove theoretical regret bounds on Deep UCB giving convergence to optimality for the weak class of CMAB problems.