Few-Shot Design Optimization by Exploiting Auxiliary Information

TL;DR

This paper introduces a neural-based few-shot optimization method that leverages auxiliary information and task history to efficiently optimize expensive black-box functions in real-world design problems.

Contribution

It presents a novel approach that uses auxiliary data and prior tasks to improve few-shot optimization performance in complex design domains.

Findings

Achieves more accurate few-shot predictions with auxiliary feedback.

Significantly outperforms existing multi-task optimization methods.

Demonstrates effectiveness in robotic hardware design and neural network tuning.

Abstract

Many real-world design problems involve optimizing an expensive black-box function $f(x)$, such as hardware design or drug discovery. Bayesian Optimization has emerged as a sample-efficient framework for this problem. However, the basic setting considered by these methods is simplified compared to real-world experimental setups, where experiments often generate a wealth of useful information. We introduce a new setting where an experiment generates high-dimensional auxiliary information $h(x)$ along with the performance measure $f(x)$; moreover, a history of previously solved tasks from the same task family is available for accelerating optimization. A key challenge of our setting is learning how to represent and utilize $h(x)$ for efficiently solving new optimization tasks beyond the task history. We develop a novel approach for this setting based on a neural model which predicts $f(x)$ for unseen designs given a few-shot context containing observations of $h(x)$. We evaluate our method on two challenging domains, robotic hardware design and neural network hyperparameter tuning, and introduce a novel design problem and large-scale benchmark for the former. On both domains, our method utilizes auxiliary feedback effectively to achieve more accurate few-shot prediction and faster optimization of design tasks, significantly outperforming several methods for multi-task optimization.