Meta-Learning Priors for Efficient Online Bayesian Regression

TL;DR

ALPaCA is a meta-learning algorithm that learns domain-specific features and priors for efficient, scalable Bayesian regression, outperforming traditional Gaussian Processes and other meta-learning methods in robotics applications.

Contribution

The paper introduces ALPaCA, a novel meta-learning approach that learns neural network features and priors for fast, data-efficient Bayesian regression in robotics.

Findings

ALPaCA outperforms kernel-based GP regression in accuracy and efficiency.

ALPaCA reduces sample complexity significantly compared to traditional methods.

ALPaCA demonstrates superior performance on robotic and human driving tasks.

Abstract

Gaussian Process (GP) regression has seen widespread use in robotics due to its generality, simplicity of use, and the utility of Bayesian predictions. The predominant implementation of GP regression is a nonparameteric kernel-based approach, as it enables fitting of arbitrary nonlinear functions. However, this approach suffers from two main drawbacks: (1) it is computationally inefficient, as computation scales poorly with the number of samples; and (2) it can be data inefficient, as encoding prior knowledge that can aid the model through the choice of kernel and associated hyperparameters is often challenging and unintuitive. In this work, we propose ALPaCA, an algorithm for efficient Bayesian regression which addresses these issues. ALPaCA uses a dataset of sample functions to learn a domain-specific, finite-dimensional feature encoding, as well as a prior over the associated weights, such that Bayesian linear regression in this feature space yields accurate online predictions of the posterior predictive density. These features are neural networks, which are trained via a meta-learning (or "learning-to-learn") approach. ALPaCA extracts all prior information directly from the dataset, rather than restricting prior information to the choice of kernel hyperparameters. Furthermore, by operating in the weight space, it substantially reduces sample complexity. We investigate the performance of ALPaCA on two simple regression problems, two simulated robotic systems, and on a lane-change driving task performed by humans. We find our approach outperforms kernel-based GP regression, as well as state of the art meta-learning approaches, thereby providing a promising plug-in tool for many regression tasks in robotics where scalability and data-efficiency are important.