5 papers
Practical Efficient Global Optimization is No-regret
Jingyi Wang, Haowei Wang, Nai-Yuan Chiang +3
Efficient global optimization (EGO) is one of the most widely used noise-free Bayesian optimization algorithms.It comprises the Gaussian process (GP) surrogate model and expected i…
Convergence Rates of Constrained Expected Improvement
Haowei Wang, Jingyi Wang, Zhongxiang Dai +3
Constrained Bayesian optimization (CBO) methods have seen significant success in black-box optimization with constraints. One of the most commonly used CBO methods is the constrain…
Bayesian Optimization with Expected Improvement: No Regret and the Choice of Incumbent
Jingyi Wang, Haowei Wang, Szu Hui Ng +1
Expected improvement (EI) is one of the most widely used acquisition functions in Bayesian optimization (BO). Despite its proven empirical success in applications, the cumulative r…
On the convergence rate of noisy Bayesian Optimization with Expected Improvement
Jingyi Wang, Haowei Wang, Nai-Yuan Chiang +1
Expected improvement (EI) is one of the most widely used acquisition functions in Bayesian optimization (BO). Despite its proven success in applications for decades, important open…
On Improved Regret Bounds In Bayesian Optimization with Gaussian Noise
Jingyi Wang, Haowei Wang, Cosmin G. Petra +1
Bayesian optimization (BO) with Gaussian process (GP) surrogate models is a powerful black-box optimization method. Acquisition functions are a critical part of a BO algorithm as t…