Pre-training helps Bayesian optimization too
Bayesian optimization (BO) has become a popular strategy for global optimization of many expensive real-world functions. Contrary to a common belief that BO is suited to optimizing black-box functions, it actually requires domain knowledge on characteristics of those functions to deploy BO successfully. Such domain knowledge often manifests in Gaussian process priors that specify initial beliefs on functions. However, even with expert knowledge, it is not an easy task to select a prior. This is especially true for hyperparameter tuning problems on complex machine learning models, where landscapes of tuning objectives are often difficult to comprehend. We seek an alternative practice for setting these functional priors. In particular, we consider the scenario where we have data from similar functions that allow us to pre-train a tighter distribution a priori. To verify our approach in realistic model training setups, we collected a large multi-task hyperparameter tuning dataset by training tens of thousands of configurations of near-state-of-the-art models on popular image and text datasets, as well as a protein sequence dataset. Our results show that on average, our method is able to locate good hyperparameters at least 3 times more efficiently than the best competing methods.
Code (1)
Tasks
Bayesian Optimizationglobal-optimizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Posterior Temperature Optimization in Variational Inference for Inverse Problems
Bayesian methods feature useful properties for solving inverse problems, such as tomographic reconstruction. The prior distribution introduces regularization, which helps solving the ill-posed problem and reduces overfit…
Bayesian OptimizationCT ReconstructionDenoisingVariational InferenceBayesian Scattering: A Principled Baseline for Uncertainty on Image Data
Uncertainty quantification for image data is dominated by complex deep learning methods, yet the field lacks an interpretable, mathematically grounded baseline. We propose Bayesian scattering to fill this gap, serving as…
Is Sequence Information All You Need for Bayesian Optimization of Antibodies?
Bayesian optimization is a natural candidate for the engineering of antibody therapeutic properties, which is often iterative and expensive. However, finding the optimal choice of surrogate model for optimization over th…
Protein Language ModelA Diffusion Approximation Theory of Momentum SGD in Nonconvex Optimization
Momentum Stochastic Gradient Descent (MSGD) algorithm has been widely applied to many nonconvex optimization problems in machine learning, e.g., training deep neural networks, variational Bayesian inference, and etc. Des…
Bayesian InferenceDimensionality ReductionStochastic OptimizationAdaptation of Engineering Wake Models using Gaussian Process Regression and High-Fidelity Simulation Data
This article investigates the optimization of yaw control inputs of a nine-turbine wind farm. The wind farm is simulated using the high-fidelity simulator SOWFA. The optimization is performed with a modifier adaptation s…
Bayesian OptimizationGaussian Processesregression