Best-Effort Adaptation

TL;DR

This paper introduces a new theoretical framework and algorithms for best-effort domain adaptation, effectively leveraging abundant source domain data to improve target domain predictions with limited labeled samples.

Contribution

It provides a discrepancy-based theoretical analysis and novel algorithms for best-effort adaptation, enhancing standard domain adaptation methods especially with scarce target data.

Findings

The proposed algorithms outperform baselines in experiments.

Theoretical bounds guide effective sample reweighting.

Improved solutions for fine-tuning scenarios.

Abstract

We study a problem of best-effort adaptation motivated by several applications and considerations, which consists of determining an accurate predictor for a target domain, for which a moderate amount of labeled samples are available, while leveraging information from another domain for which substantially more labeled samples are at one's disposal. We present a new and general discrepancy-based theoretical analysis of sample reweighting methods, including bounds holding uniformly over the weights. We show how these bounds can guide the design of learning algorithms that we discuss in detail. We further show that our learning guarantees and algorithms provide improved solutions for standard domain adaptation problems, for which few labeled data or none are available from the target domain. We finally report the results of a series of experiments demonstrating the effectiveness of our best-effort adaptation and domain adaptation algorithms, as well as comparisons with several baselines. We also discuss how our analysis can benefit the design of principled solutions for fine-tuning.