Portfolio allocation for Bayesian optimization
Matthew D. Hoffman, Eric Brochu, Nando de Freitas · 2011
Bayesian optimization with Gaussian processes has become an increasingly popular tool in the machine learning community. It is efficient and can be used when very little is known about the objective function, making it popular in expensive black-box optimization scenarios. It uses Bayesian methods to sample the objective efficiently using an acquisition function which incorporates the posterior estimate of the objective. However, there are several different parameterized acquisition functions in the literature, and it is often unclear which one to use. Instead of using a single acquisition function, we adopt a portfolio of acquisition functions governed by an online multi-armed bandit strategy. We propose several portfolio strategies, the best of which we call GP-Hedge, and show that this method outperforms the best individual acquisition function. We also provide a theoretical bound on the algorithm’s performance. 1
Cited by 114 works.
Authors
References
- Numerical optimization
- Gaussian Processes for Machine Learning
- Efficient Global Optimization of Expensive Black-Box Functions
- Prediction, Learning, and Games
- Approximate Bayesian Inference for Latent Gaussian models by using Integrated Nested Laplace Approximations
- A Taxonomy of Global Optimization Methods Based on Response Surfaces
- 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
- Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting
- A New Method of Locating the Maximum Point of an Arbitrary Multipeak Curve in the Presence of Noise