Meta-Learning Acquisition Functions for Transfer Learning in Bayesian Optimization
ICLR 20 10-2-2020
PreviousLearning to Generalize: Meta-Learning for Domain GeneralizationNextNetwork Architecture Search for Domain Adaptation
Last updated
ICLR 20 10-2-2020
Last updated
NOTE: read this paper again in details. It looks a novel direction
Transferring knowledge across tasks to improve data-efficiency is one of the open key challenges in the field of global black-box optimization. (how about not black box?)
limitation of current method:
Readily available algorithms are typically designed to be universal optimizers and, therefore, often suboptimal for specific tasks.
Method in the paper:
We propose a novel transfer learning method to obtain customized optimizers within the well-established framework of Bayesian optimization, allowing our algorithm to utilize the proven generalization capabilities of Gaussian processes surrogate model.
Using reinforcement learning to meta-train an acquisition function (AF) on a set of related tasks, the proposed method learns to extract implicit structural information and to exploit it for improved data-efficiency.
Usually Bayesian Optimization (BO) is used for the problem
Probabilistic surrogate model (e.g., GP) to interpolate between data points
Sampling strategy (acquisition function, AF) based on surrogate model
Transfer learning is used to increase the data-efficiency by transferring knowledge across task instances
Retain the proven structure of BO, keep the powerful GP surrogate model
Replace the AF part with neural AF to obtain task-specific AFs by transfer learning
Train neural AFs using RL: so no need for gradients of
