Please use this identifier to cite or link to this item:
|Scopus||Web of Science®||Altmetric|
|Title:||PAC-Bayes meta-learning with implicit task-specific posteriors|
|Citation:||IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023; 45(1):841-851|
|Publisher:||Institute of Electrical and Electronics Engineers|
|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 http://www.ieee.org/publications_standards/publications/rights/index.html for more information.|
|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.