# A Note on Bounding Regret of the C2UCB Contextual Combinatorial Bandit

arXiv: https://arxiv.org/abs/1902.07500 · HTML: https://mlsanity.com/paper/1902.07500/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Feb 2019.

## Built on by (most cited first, 1 of 1)

- [No DBA? No regret! Multi-armed bandits for index tuning of analytical and HTAP workloads with provable guarantees](https://mlsanity.com/paper/2108.10130/) (2021)

## Abstract (arXiv)

We revisit the proof by Qin et al. (2014) of bounded regret of the C2UCB contextual combinatorial bandit. We demonstrate an error in the proof of volumetric expansion of the moment matrix, used in upper bounding a function of context vector norms. We prove a relaxed inequality that yields the originally-stated regret bound.