arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.02265cs.LGstat.ML
收藏

变分贝叶斯元学习

Meta-Learning with Variational Bayes

Lucas D. Lingle

摘要:

元学习领域寻求提高当今机器学习系统有效适应少量数据的能力。通常,这是通过使用参数化更新规则训练系统来实现的,以基于监督或奖励函数来改进任务相关目标。然而,在许多领域的实际利益,任务数据是未标记的,或奖励功能是不可用的。在本文中,我们介绍了一种新的方法来解决更普遍的问题,生成元学习,我们认为这是一个重要的先决条件,获得人类水平的认知灵活性的人工代理,并可以受益于许多实际应用的道路上。我们的贡献利用AEVB框架和平均场变分贝叶斯,并创建快速适应的潜在空间生成模型。我们贡献的核心是一个新的结果,表明对于广泛的一类深度生成潜变量模型,相关的VB更新不依赖于任何生成神经网络。我们的方法的理论优点反映在实证实验中。

英文摘要:

The field of meta-learning seeks to improve the ability of today's machine learning systems to adapt efficiently to small amounts of data. Typically this is accomplished by training a system with a parametrized update rule to improve a task-relevant objective based on supervision or a reward function. However, in many domains of practical interest, task data is unlabeled, or reward functions are unavailable. In this paper we introduce a new approach to address the more general problem of generative meta-learning, which we argue is an important prerequisite for obtaining human-level cognitive flexibility in artificial agents, and can benefit many practical applications along the way. Our contribution leverages the AEVB framework and mean-field variational Bayes, and creates fast-adapting latent-space generative models. At the heart of our contribution is a new result, showing that for a broad class of deep generative latent variable models, the relevant VB updates do not depend on any generative neural network. The theoretical merits of our approach are reflected in empirical 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。

↑