Effective Meta-Regularization by Kernelized Proximal RegularizationDownload PDF

Published: 09 Nov 2021, Last Modified: 05 May 2023NeurIPS 2021 PosterReaders: Everyone
Keywords: meta-learning
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.
Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.
Supplementary Material: zip
Code: https://github.com/ws-jiang/MetaProx
15 Replies