Adaptive transfer learning

Henry Reeve*, Timothy Cannings, Richard J. Samworth

*Corresponding author for this work

Research output: Contribution to journalArticle (Academic Journal)peer-review

Abstract

In transfer learning, we wish to make inference about a target population
when we have access to data both from the distribution itself, and from a different but related source distribution. We introduce a flexible framework for transfer learning in the context of binary classification, allowing for covariate-dependent relationships between the source and target distributions that are not required to preserve the Bayes decision boundary. Our main contributions are to derive the minimax optimal rates of convergence (up to poly-logarithmic factors) in this problem, and show that the optimal rate can be achieved by an algorithm that adapts to key aspects of the unknown transfer relationship, as well as the smoothness and tail parameters of our distributional classes. This optimal rate turns out to have several regimes, depending on the interplay between the relative sample sizes and the strength of the transfer relationship, and our algorithm achieves optimality by careful, decision tree-based calibration of local nearest-neighbour procedures.
Original languageEnglish
JournalAnnals of Statistics
Publication statusAccepted/In press - 8 Jun 2021

Keywords

  • Transfer learning
  • Non-parametric
  • Minimax
  • Statistics
  • Nearest neighbour classifier
  • Decision tree

Fingerprint

Dive into the research topics of 'Adaptive transfer learning'. Together they form a unique fingerprint.

Cite this