# Transfer Bayesian Meta-learning via Weighted Free Energy Minimization

arXiv: https://arxiv.org/abs/2106.10711 · HTML: https://mlsanity.com/paper/2106.10711/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 21 references that are in the map.
- First posted on arXiv 20 Jun 2021.

## Builds on (most cited first, 13 of 13)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm](https://mlsanity.com/paper/1608.04471/) (2016)
- [Bayesian Model-Agnostic Meta-Learning](https://mlsanity.com/paper/1806.03836/) (2018)
- [PACOH: Bayes-Optimal Meta-Learning with PAC-Guarantees](https://mlsanity.com/paper/2002.05551/) (2020)
- [Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theory](https://mlsanity.com/paper/1711.01244/) (2017)
- [A PAC-Bayesian bound for Lifelong Learning](https://mlsanity.com/paper/1311.2838/) (2013)
- [Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distribution Tasks](https://mlsanity.com/paper/1905.12917/) (2019)
- [Meta-Learning Reliable Priors in the Function Space](https://mlsanity.com/paper/2106.03195/) (2021)
- [Meta-Learning Mean Functions for Gaussian Processes](https://mlsanity.com/paper/1901.08098/) (2019)
- [Transfer Meta-Learning: Information-Theoretic Bounds and Information Meta-Risk Minimization](https://mlsanity.com/paper/2011.02872/) (2020)
- [Meta-Learning to Communicate: Fast End-to-End Training for Fading Channels](https://mlsanity.com/paper/1910.09945/) (2019)
- [Information-Theoretic Bounds on Transfer Generalization Gap Based on Jensen-Shannon Divergence](https://mlsanity.com/paper/2010.09484/) (2020)

## Abstract (arXiv)

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.