Adaptive Random Matrices in Gaussian Bandits: Spectral Universality and Selection-Induced Outliers

arXiv:2609.30321 · stat.ML, cs.LG, math.PR, math.ST, stat.TH · Submitted 2026-09-23 · Read on arXiv

stat.ML, cs.LG, math.PR, math.ST, stat.TH

Submitted: 2026-09-23

Updated: 2026-09-23

Terminology

• Trace — 10× in this paper · explained in 2 episodes
• Regret — 7× in this paper · explained in 3 episodes
• Contextual Bandits — 4× in this paper · explained in 3 episodes
• Action Space — 2× in this paper · explained in 1 episode
• Adaptive Sampling — 1× in this paper · explained in 1 episode
• Adaptive Selection — 1× in this paper · explained in 1 episode
• Adaptivity — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Contextual Bandit Problem — 1× in this paper · explained in 2 episodes
• First-Order Transition — 1× in this paper · explained in 2 episodes
• Uncertainty Quantification — 1× in this paper · explained in 8 episodes
• Wasserstein Distance — 1× in this paper · explained in 4 episodes

Sources

• Eigenvalues of Large Sample Covariance Matrices of Spiked Population Models
• Phase transition of the largest eigenvalue for non-null complex sample covariance matrices
• Linear Bandits in High Dimension and Recommendation Systems
• Statistical Inference under Adaptive Sampling with LinUCB
• A Smoothed Analysis of the Greedy Algorithm for the Linear Contextual Bandit Problem
• A Tutorial on Thompson Sampling

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• One Permutation Is All You Need: Fast, Deterministic Feature Importance and Model Stress-Testing
• Online Conformal Prediction for Non-Exchangeable Panel Data
• Deep Time-Series Forecasting in 10 Years: A Survey