arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.08949cs.LGstat.ML
收藏

概率主动元学习

Probabilistic Active Meta-Learning

University College London(伦敦大学学院);Imperial College London(帝国理工学院)

Jean Kaddour, Steindór Sæmundsson, Marc Peter Deisenroth

摘要:

数据高效的学习算法在数据汇集昂贵的许多实际应用中是必不可少的,例如,在机器人技术中的应用为了解决这个问题,元学习算法使用关于任务的先前经验来有效地学习新的相关任务。通常,假设给定或随机选择一组训练任务。然而,这种设置没有考虑到在现实生活中从头开始训练模型时自然产生的顺序性质:我们如何以数据高效的方式收集一组训练任务?在这项工作中,我们引入了任务选择的基础上先前的经验到一个元学习算法的概念化的学习者和积极的元学习设置使用概率潜在变量模型。我们提供的经验证据表明,与模拟机器人实验的强基线相比,我们的方法提高了数据效率。

英文摘要:

Data-efficient learning algorithms are essential in many practical applications where data collection is expensive, e.g., in robotics due to the wear and tear. To address this problem, meta-learning algorithms use prior experience about tasks to learn new, related tasks efficiently. Typically, a set of training tasks is assumed given or randomly chosen. However, this setting does not take into account the sequential nature that naturally arises when training a model from scratch in real-life: how do we collect a set of training tasks in a data-efficient manner? In this work, we introduce task selection based on prior experience into a meta-learning algorithm by conceptualizing the learner and the active meta-learning setting using a probabilistic latent variable model. We provide empirical evidence that our approach improves data-efficiency when compared to strong baselines on simulated robotic experiments.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑