A survey on domain adaptation theory: learning bounds and theoretical guarantees

TL;DR

This survey reviews the latest theoretical results in domain adaptation, a transfer learning sub-field where the data distribution changes but the task remains the same, focusing on learning bounds and guarantees.

Contribution

It provides a comprehensive overview of recent theoretical developments and learning bounds in domain adaptation, highlighting key results and frameworks.

Findings

Summarizes various statistical learning bounds for domain adaptation.

Highlights the importance of theoretical guarantees in transfer learning.

Provides an up-to-date overview of domain adaptation research.

Abstract

All famous machine learning algorithms that comprise both supervised and semi-supervised learning work well only under a common assumption: the training and test data follow the same distribution. When the distribution changes, most statistical models must be reconstructed from newly collected data, which for some applications can be costly or impossible to obtain. Therefore, it has become necessary to develop approaches that reduce the need and the effort to obtain new labeled samples by exploiting data that are available in related areas, and using these further across similar fields. This has given rise to a new machine learning framework known as transfer learning: a learning setting inspired by the capability of a human being to extrapolate knowledge across tasks to learn more efficiently. Despite a large amount of different transfer learning scenarios, the main objective of this survey is to provide an overview of the state-of-the-art theoretical results in a specific, and arguably the most popular, sub-field of transfer learning, called domain adaptation. In this sub-field, the data distribution is assumed to change across the training and the test data, while the learning task remains the same. We provide a first up-to-date description of existing results related to domain adaptation problem that cover learning bounds based on different statistical learning frameworks.