Online Meta-Learning on Non-convex Setting

10/22/2019
by   Zhenxun Zhuang, et al.
0

The online meta-learning framework is designed for the continual lifelong learning setting. It bridges two fields: meta-learning which tries to extract prior knowledge from existing tasks for fast learning of future tasks, and online-learning which focuses on the sequential setting in which problems are revealed one by one. In this paper, we generalize the original framework from convex to non-convex setting, and introduce the local regret as the alternative performance measure. We then apply this framework to stochastic settings, and show theoretically that it enjoys a logarithmic local regret, and is robust to any hyperparameter initialization. The empirical test on a real-world task demonstrates its superiority compared with traditional methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/19/2021

Learning-to-learn non-convex piecewise-Lipschitz functions

We analyze the meta-learning of the initialization and step-size of lear...
research
02/22/2019

Online Meta-Learning

A central capability of intelligent systems is the ability to continuous...
research
09/29/2021

Dynamic Regret Analysis for Online Meta-Learning

The online meta-learning framework has arisen as a powerful tool for the...
research
12/16/2020

Inexact-ADMM Based Federated Meta-Learning for Fast and Continual Edge Learning

In order to meet the requirements for performance, safety, and latency i...
research
08/21/2021

Fairness-Aware Online Meta-learning

In contrast to offline working fashions, two research paradigms are devi...
research
07/05/2023

Meta-Learning Adversarial Bandit Algorithms

We study online meta-learning with bandit feedback, with the goal of imp...
research
06/06/2019

Adaptive Gradient-Based Meta-Learning Methods

We build a theoretical framework for understanding practical meta-learni...

Please sign up or login with your details

Forgot password? Click here to reset