Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Journal article
Title: PAC-Bayes meta-learning with implicit task-specific posteriors
Author: Nguyen, C.
Do, T.-T.
Carneiro, G.
Citation: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023; 45(1):841-851
Publisher: Institute of Electrical and Electronics Engineers
Issue Date: 2023
ISSN: 0162-8828
Statement of
Cuong Nguyen, Thanh-Toan Do, and Gustavo Carneiro
Abstract: We introduce a new and rigorously-formulated PAC-Bayes meta-learning algorithm that solves few-shot learning. Our proposed method extends the PAC-Bayes framework from a single-task setting to the meta-learning multiple-task setting to upper-bound the error evaluated on any, even unseen, tasks and samples. We also propose a generative-based approach to estimate the posterior of task-specific model parameters more expressively compared to the usual assumption based on a multivariate normal distribution with a diagonal covariance matrix. We show that the models trained with our proposed meta-learning algorithm are well-calibrated and accurate, with state-of-the-art calibration errors while still being competitive on classification results on few-shot classification (mini-ImageNet and tiered-ImageNet) and regression (multi-modal task-distribution regression) benchmarks.
Keywords: PAC Bayes; meta-learning; few-shot learning; transfer learning
Description: Published January 2023
Rights: © 2021 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See for more information.
DOI: 10.1109/TPAMI.2022.3147798
Grant ID:
Appears in Collections:Computer Science publications

Files in This Item:
There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.