Zheng Xie

SEP 9, 2026 · PREPRINT

Meta-LinEXP3: Online-within-Online Learning for Adversarial Linear Contextual Bandits

arXiv

This is a theoretical computer science contribution proposing a novel algorithm with regret bounds and limited experimental validation; it raises and addresses a computational learning problem rather than answering a clinical or established empirical question.

AUG 16, 2026 · PREPRINT

PERO: Efficient Robust Post-Training Foundation Models for Encrypted Traffic Classification

arXiv

This is a computational methods paper proposing a novel algorithm (PERO) for machine learning model optimization, with no clinical outcome, patient population, or real-world validation against established standards.