Optimization
Stopping Bayesian Optimization with Probabilistic Regret Bounds
Monte Carlo stopping rules in a manner that is both sample efficient and robust to estimation error.
Boosting Adversarial Transferability by Achieving Flat Local Maxima
Specifically, we randomly sample an example and adopt a first-order procedure to approximate the Hessian/vector product, which makes computing more efficient by interpolating two neighboring gradients.
Iterative Reachability Estimation for Safe Reinforcement Learning
We theoretically establish that our algorithms almost surely converge to locally optimal policies of our safe optimization framework.
Data-driven Optimal Filtering for Linear Systems with Unknown Noise Covariances
This paper examines learning the optimal filtering policy, known as the Kalman gain, for a linear system with unknown noise covariance matrices using noisy output data. The learning problem is formulated as a stochastic policy optimization problem, aiming to minimize the output prediction error. This formulation provides a direct bridge between data-driven optimal control and, its dual, optimal filtering.
Framework and Benchmarks for Combinatorial and Mixed-variable Bayesian Optimization
Leveraging this flexibility, we implement 47 novel MCBO algorithms and benchmark them against seven existing MCBO solvers and five standard black-box optimization algorithms on ten tasks, conducting over 4000 experiments.