Adaptive Random Matrices in Gaussian Bandits: Spectral Universality and Selection-Induced Outliers
arXiv:2609.30321v1 Announce Type: new Abstract: Adaptive arm selection changes the distribution of the observations collected by a bandit algorithm, but it need not change their limiting empirical spectrum. We study Gaussian bandit designs in which the dimension and the number of observations grow…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-09-28 04:00 · arXiv stat.ML
Adaptive Random Matrices in Gaussian Bandits: Spectral Universality and Selection-Induced Outliers