🏢 Morgan Stanley
Stopping Bayesian Optimization with Probabilistic Regret Bounds
·3802 words·18 mins·
loading
·
loading
Machine Learning
Optimization
🏢 Morgan Stanley
This paper presents a novel probabilistic regret bound (PRB) framework for Bayesian optimization, replacing the traditional fixed-budget stopping rule with a criterion based on the probability of find…
Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes
·1443 words·7 mins·
loading
·
loading
Machine Learning
Reinforcement Learning
🏢 Morgan Stanley
This paper proposes a novel, statistically efficient offline policy evaluation method robust to environmental shifts and unobserved confounding, providing sharp bounds with theoretical guarantees.