NeurIPS 2021poster7 citations
Effective Meta-Regularization by Kernelized Proximal Regularization
Weisen Jiang, James Kwok, Yu Zhang
Abstract
We study the problem of meta-learning, which has proved to be advantageous to accelerate learning new tasks with a few samples. The recent approaches based on deep kernels achieve the state-of-the-art performance. However, the regularizers in their base learners are not learnable. In this paper, we propose an algorithm called MetaProx to learn a proximal regularizer for the base learner. We theoretically establish the convergence of MetaProx. Experimental results confirm the advantage of the proposed algorithm.
meta-learning
BibTeX
@inproceedings{
jiang2021effective,
title={Effective Meta-Regularization by Kernelized Proximal Regularization},
author={Weisen Jiang and James Kwok and Yu Zhang},
booktitle={Advances in Neural Information Processing Systems},
editor={A. Beygelzimer and Y. Dauphin and P. Liang and J. Wortman Vaughan},
year={2021},
url={https://openreview.net/forum?id=mekyxmlLJNd}
}