@inproceedings{67aefcb069e14563917b0995cd9058f8,
title = "Transfer Bayesian meta-learning via weighted free energy minimization",
abstract = "Meta-learning optimizes the hyperparameters of a training procedure, such as its initialization, kernel, or learning rate, based on data sampled from a number of auxiliary tasks. A key underlying assumption is that the auxiliary tasks - known as meta-training tasks - share the same generating distribution as the tasks to be encountered at deployment time - known as meta-test tasks. This may, however, not be the case when the test environment differ from the meta-training conditions. To address shifts in task generating distribution between meta-training and meta-testing phases, this paper introduces weighted free energy minimization (WFEM) for transfer meta-learning. We instantiate the proposed approach for non-parametric Bayesian regression and classification via Gaussian Processes (GPs). The method is validated on a toy sinusoidal regression problem, as well as on classification using miniImagenet and CUB data sets, through comparison with standard meta-learning of GP priors as implemented by PACOH.",
keywords = "Transfer Meta-learning, Gaussian Process, Bayesian learning",
author = "Sharu Jose and Osvaldo Simeone and Yunchuan Zhang",
year = "2021",
month = nov,
day = "15",
doi = "10.1109/MLSP52302.2021.9596239",
language = "English",
isbn = "9781665411844 (PoD)",
series = "Proceedings of the IEEE Signal Processing Society Workshop",
publisher = "IEEE",
booktitle = "2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)",
note = "2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP), MLSP 2021 ; Conference date: 20-09-2021 Through 23-09-2021",
}