Learning an Explicit Hyperparameter Prediction Function Conditioned on Tasks

TL;DR

This paper proposes a meta-learning approach that learns an explicit hyper-parameter prediction function conditioned on tasks, enhancing adaptability and generalization across diverse query tasks in various applications.

Contribution

It introduces a novel meta-learner that predicts hyper-parameters based on tasks, providing greater flexibility than fixed hyper-parameter methods and enabling theoretical analysis of generalization bounds.

Findings

The method improves adaptability in few-shot regression and classification.

The approach enhances domain generalization capabilities.

Theoretical analysis supports the generalization performance of the meta-learner.

Abstract

Meta learning has attracted much attention recently in machine learning community. Contrary to conventional machine learning aiming to learn inherent prediction rules to predict labels for new query data, meta learning aims to learn the learning methodology for machine learning from observed tasks, so as to generalize to new query tasks by leveraging the meta-learned learning methodology. In this study, we interpret such learning methodology as learning an explicit hyper-parameter prediction function shared by all training tasks. Specifically, this function is represented as a parameterized function called meta-learner, mapping from a training/test task to its suitable hyper-parameter setting, extracted from a pre-specified function set called meta learning machine. Such setting guarantees that the meta-learned learning methodology is able to flexibly fit diverse query tasks, instead of only obtaining fixed hyper-parameters by many current meta learning methods, with less adaptability to query task's variations. Such understanding of meta learning also makes it easily succeed from traditional learning theory for analyzing its generalization bounds with general losses/tasks/models. The theory naturally leads to some feasible controlling strategies for ameliorating the quality of the extracted meta-learner, verified to be able to finely ameliorate its generalization capability in some typical meta learning applications, including few-shot regression, few-shot classification and domain generalization.