Abstract
We analyze new generalization bounds for deep learning models trained by transfer learning from a source to a target task. Our bounds utilize a quantity called the majority predictor accuracy, which can be computed efficiently from data. We show that our theory is useful in practice since it implies that the majority predictor accuracy can be used as a transferability measure, a fact that is also validated by our experiments.
Original language | English |
---|---|
Title of host publication | Proceedings of 2022 International Symposium on Information Theory and Its Applications, ISITA 2022 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 139-143 |
Number of pages | 5 |
ISBN (Electronic) | 9784885523410 |
State | Published - 2022 |
Externally published | Yes |
Event | 17th International Symposium on Information Theory and Its Applications, ISITA 2022 - Tsukuba, Ibaraki, Japan Duration: 17 Oct 2022 → 19 Oct 2022 |
Publication series
Name | Proceedings of 2022 International Symposium on Information Theory and Its Applications, ISITA 2022 |
---|
Conference
Conference | 17th International Symposium on Information Theory and Its Applications, ISITA 2022 |
---|---|
Country/Territory | Japan |
City | Tsukuba, Ibaraki |
Period | 17/10/22 → 19/10/22 |
Bibliographical note
Publisher Copyright:© 2022 IEICE.