LGFeb 20, 2022

A History of Meta-gradient: Gradient Methods for Meta-learning

arXiv:2202.09701v112 citations
AI Analysis

This is an incremental review paper for researchers in meta-learning, summarizing existing work without introducing novel contributions.

The paper reviews the history of gradient-based meta-learning methods, specifically those that adapt learning rate meta-parameters, without presenting new experimental results or numerical findings.

The history of meta-learning methods based on gradient descent is reviewed, focusing primarily on methods that adapt step-size (learning rate) meta-parameters.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes