# Neural Combinatorial Clustered Bandits for Recommendation Systems

arXiv: https://arxiv.org/abs/2410.14586 · HTML: https://mlsanity.com/paper/2410.14586/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 22 references that are in the map.
- First posted on arXiv 18 Oct 2024.

## Builds on (most cited first, 11 of 11)

- [On Exact Computation with an Infinitely Wide Neural Net](https://mlsanity.com/paper/1904.11955/) (2019)
- [Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks](https://mlsanity.com/paper/1905.13210/) (2019)
- [Reinforcement Learning in Feature Space: Matrix Bandit, Kernels, and Regret Bound](https://mlsanity.com/paper/1905.10389/) (2019)
- [Finite-Time Analysis of Kernelised Contextual Bandits](https://mlsanity.com/paper/1309.6869/) (2013)
- [Neural Thompson Sampling](https://mlsanity.com/paper/2010.00827/) (2020)
- [Online Clustering of Bandits](https://mlsanity.com/paper/1401.8257/) (2014)
- [Cascading Bandits for Large-Scale Recommendation Problems](https://mlsanity.com/paper/1603.05359/) (2016)
- [Efficient Learning in Large-Scale Combinatorial Semi-Bandits](https://mlsanity.com/paper/1406.7443/) (2014)
- [Multi-facet Contextual Bandits: A Neural Network Perspective](https://mlsanity.com/paper/2106.03039/) (2021)
- [The Hardness Analysis of Thompson Sampling for Combinatorial Semi-bandits with Greedy Oracle](https://mlsanity.com/paper/2111.04295/) (2021)
- [Contextual Combinatorial Multi-output GP Bandits with Group Constraints](https://mlsanity.com/paper/2111.14778/) (2021)

## Built on by (most cited first, 2 of 2)

- [Provable Anytime Ensemble Sampling Algorithms in Nonlinear Contextual Bandits](https://mlsanity.com/paper/2510.10730/) (2025)
- [Combinatorial Rising Bandits](https://mlsanity.com/paper/2412.00798/) (2024)

## Abstract (arXiv)

We consider the contextual combinatorial bandit setting where in each round, the learning agent, e.g., a recommender system, selects a subset of "arms," e.g., products, and observes rewards for both the individual base arms, which are a function of known features (called "context"), and the super arm (the subset of arms), which is a function of the base arm rewards. The agent's goal is to simultaneously learn the unknown reward functions and choose the highest-reward arms. For example, the "reward" may represent a user's probability of clicking on one of the recommended products. Conventional bandit models, however, employ restrictive reward function models in order to obtain performance guarantees. We make use of deep neural networks to estimate and learn the unknown reward functions and propose Neural UCB Clustering (NeUClust), which adopts a clustering approach to select the super arm in every round by exploiting underlying structure in the context space. Unlike prior neural bandit works, NeUClust uses a neural network to estimate the super arm reward and select the super arm, thus eliminating the need for a known optimization oracle. We non-trivially extend prior neural combinatorial bandit works to prove that NeUClust achieves widetildeOleft(widetilded√Tright) regret, where widetilded is the effective dimension of a neural tangent kernel matrix, T the number of rounds. Experiments on real world recommendation datasets show that NeUClust achieves better regret and reward than other contextual combinatorial and neural bandit algorithms.