Practicality of generalization guarantees for unsupervised domain adaptation with neural networks
Artikel i vetenskaplig tidskrift, 2022

Understanding generalization is crucial to confidently engineer and deploy machine learning models, especially when deployment implies a shift in the data domain. For such domain adaptation problems, we seek generalization bounds which are tractably computable and tight. If these desiderata can be reached, the bounds can serve as guarantees for adequate
performance in deployment. However, in applications where deep neural networks are the models of choice, deriving results which fulfill these remains an unresolved challenge; most existing bounds are either vacuous or has non-estimable terms, even in favorable conditions.
In this work, we evaluate existing bounds from the literature with potential to satisfy our desiderata on domain adaptation image classification tasks, where deep neural networks are preferred. We find that all bounds are vacuous and that sample generalization terms account for much of the observed looseness, especially when these terms interact with measures of
domain shift. To overcome this and arrive at the tightest possible results, we combine each bound with recent data-dependent PAC-Bayes analysis, greatly improving the guarantees.
We find that, when domain overlap can be assumed, a simple importance weighting extension of previous work provides the tightest estimable bound. Finally, we study which terms dominate the bounds and identify possible directions for further improvement.

Författare

Adam Breitholtz

Chalmers, Data- och informationsteknik, Data Science och AI

Fredrik Johansson

Chalmers, Data- och informationsteknik, Data Science och AI

Transactions on Machine Learning Research

Vol. 10

Förutsättningar för inlärning av överförbara koncept

Wallenberg AI, Autonomous Systems and Software Program, 2020-08-01 -- 2025-08-01.

Infrastruktur

C3SE (Chalmers Centre for Computational Science and Engineering)

Ämneskategorier

Signalbehandling

Datorseende och robotik (autonoma system)

Matematisk analys

Mer information

Senast uppdaterat

2023-10-26