Online-Within-Online Meta-Learning
We study the problem of learning a series of tasks in a fully online Meta-Learning setting. The goal is to exploit similarities among the tasks to incrementally adapt an inner online algorithm in order to incur a low averaged cumulative error over the tasks. We focus on a family of inner algorithms based on a parametrized variant of online Mirror Descent. The inner algorithm is incrementally adapted by an online Mirror Descent meta-algorithm using the corresponding within-task minimum regularized empirical risk as the meta-loss. In order to keep the process fully online, we approximate the meta-subgradients by the online inner algorithm. An upper bound on the approximation error allows us to derive a cumulative error bound for the proposed method. Our analysis can also be converted to the statistical setting by online-to-batch arguments. We instantiate two examples of the framework in which the meta-parameter is either a common bias vector or feature map. Finally, preliminary numerical experiments confirm our theoretical findings.
Code (1)
Tasks
Meta-LearningSimilar Papers 제목 키워드 기반
Mining Online Discussion Forums for Metaphors
We present an approach to mining online forums for figurative language such as metaphor. We target in particular online discussions within the illness and the political conflict domains, with a view to constructing corpo…
Fast On-Device Adaptation for Spiking Neural Networks via Online-Within-Online Meta-Learning
Spiking Neural Networks (SNNs) have recently gained popularity as machine learning models for on-device edge intelligence for applications such as mobile healthcare management and natural language processing due to their…
Lifelong learningManagementMeta-LearningMeta-LinEXP3: Online-within-Online Learning for Adversarial Linear Contextual Bandits
Meta-learning has emerged as an effective paradigm for transferring knowledge across sequential bandit tasks. While substantial progress has been made for stochastic bandits and non-contextual adversarial bandits, meta-l…
Accelerating Distributed Online Meta-Learning via Multi-Agent Collaboration under Limited Communication
Online meta-learning is emerging as an enabling technique for achieving edge intelligence in the IoT ecosystem. Nevertheless, to learn a good meta-model for within-task fast adaptation, a single agent alone has to learn …
Meta-LearningA CMDP-within-online framework for Meta-Safe Reinforcement Learning
Meta-reinforcement learning has widely been used as a learning-to-learn framework to solve unseen tasks with limited experience. However, the aspect of constraint violations has not been adequately addressed in the exist…
Meta-LearningMeta Reinforcement Learningreinforcement-learningReinforcement Learning+1