Limits of Transfer Learning (LOD 2020)

Under what circumstances does transfer learning *actually* work?

Presentation from the Sixth International Conference on Machine Learning, Optimization, and Data Science (LOD) – July 19-23, 2020 – Certosa di Pontignano, Siena – Tuscany, Italy.

Abstract:
Transfer learning involves taking information and insight
from one problem domain and applying it to a new problem domain.
Although widely used in practice, theory for transfer learning remains
less well-developed. To address this, we prove several novel results related
to transfer learning, showing the need to carefully select which sets of
information to transfer and the need for dependence between transferred
information and target problems. Furthermore, we prove how the degree
of probabilistic change in an algorithm using transfer learning places an
upper bound on the amount of improvement possible. These results build
on the algorithmic search framework for machine learning, allowing the
results to apply to a wide range of learning problems using transfer