Research Article
Isolating the Impact of Dimensionality on Bandit Regret via Fixed-Gap Gaussian Environments
@INPROCEEDINGS{10.4108/eai.22-5-2026.2365143, author={Luhui Zheng}, title={Isolating the Impact of Dimensionality on Bandit Regret via Fixed-Gap Gaussian Environments}, proceedings={Proceedings of the 4th International Conference on Image, Algorithms, and Artificial Intelligence, ICIAAI 2026, 22-24 May 2026, Singapore, Singapore}, publisher={EAI}, proceedings_a={ICIAAI}, year={2026}, month={8}, keywords={Multi-Armed Bandits Action Space Scalability Best Arm Identification Subsampling}, doi={10.4108/eai.22-5-2026.2365143} }- Luhui Zheng
Year: 2026
Isolating the Impact of Dimensionality on Bandit Regret via Fixed-Gap Gaussian Environments
ICIAAI
EAI
DOI: 10.4108/eai.22-5-2026.2365143
Abstract
This study tests how Explore-Then-Commit (ETC), Upper Confidence Bound (UCB), and Thompson Sampling (TS) behave in a static setting where the action space size, K, varies from 10 to 2,400. A Fixed-Gap Gaussian Environment based on MovieLens data is used to ensure the task difficulty stays the same. Experiments show that performance gets worse for every algorithm as K increases. ETC fails the most, with identification accuracy dropping below 20% because it wastes too much budget on exploration. UCB and TS do better but still show linear regret growth. This implies that probabilistic exploration is not enough to handle a massive number of sub-optimal arms. The findings suggest that standard strategies need structural changes, like subsampling, to work efficiently in large-scale environments.
