Bayesian Optimization for Dynamic Problems

2018/03/09 by Favour Nyikosa, Nyikosa, Favour M., Michael A. Osborne +3 · 2 citations
Computer Science · Decision Sciences · #Advanced Bandit Algorithms Research #Advanced Multi-Objective Optimization Algorithms #FOS: Computer and information sciences #Gaussian Processes and Bayesian Inference #Machine Learning (stat.ML)

paper · pdf · doi:10.48550/arxiv.1803.03432

openalex publication_date 2018/03/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We propose practical extensions to Bayesian optimization for solving dynamic problems. We model dynamic objective functions using spatiotemporal Gaussian process priors which capture all the instances of the functions over time. Our extensions to Bayesian optimization use the information learnt from this model to guide the tracking of a temporally evolving minimum. By exploiting temporal correlations, the proposed method also determines when to make evaluations, how fast to make those evaluations, and it induces an appropriate budget of steps based on the available information. Lastly, we evaluate our technique on synthetic and real-world problems.

Citations

• Algorithm 887
• A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning
• Lipschitzian optimization without the Lipschitz constant
• Taking the Human Out of the Loop: A Review of Bayesian Optimization
• Time-Varying Gaussian Process Bandit Optimization

Cited by

• Robust, Online, and Adaptive Decentralized Gaussian Processes
• Asymptotic Performance of Time-Varying Bayesian Optimization

Related

• Local Nonstationarity for Efficient Bayesian Optimization
• A Tutorial on Bayesian Optimization
• This Too Shall Pass: Removing Stale Observations in Dynamic Bayesian Optimization
• Event-Triggered Time-Varying Bayesian Optimization
• Warm Starting Bayesian Optimization