2 papers
cs.LG2026
Safety Generalization Under Distribution Shift in Safe Reinforcement Learning: A Diabetes Testbed
Minjae Kwon, Josephine Lamp, Lu Feng
Safe Reinforcement Learning (RL) algorithms are typically evaluated under fixed training conditions. We investigate whether training-time safety guarantees transfer to deployment u…
cs.CR2024
DP-RuL: Differentially-Private Rule Learning for Clinical Decision Support Systems
Josephine Lamp, Lu Feng, David Evans
Serious privacy concerns arise with the use of patient data in rule-based clinical decision support systems (CDSS). The goal of a privacy-preserving CDSS is to learn a population r…