arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.15569cs.LGstat.ML
收藏

基于Hilbert余集学习的风险界

Risk Bounds for Learning via Hilbert Coresets

Systems & Technology Research(系统与技术研究公司)

Spencer Douglas, Piyush Kumar, R. K. Prasanth

摘要:

我们开发了一种形式主义,通过希尔伯特coresets方法在一个转导框架内的监督分类任务的预期全样本风险的随机上界。我们显式地计算复杂数据集和复杂假设类(如最先进的深度神经网络架构)的严格和有意义的边界。我们开发的边界表现出良好的性质:i)边界在假设空间中是不均匀的,ii)在许多实际例子中,通过适当选择假设空间上的先验和训练数据相关的后验分布,边界变得有效确定,以及iii)随着训练集大小的增加,边界变得明显更好。最后,我们也提出一些想法,以供未来的研究探讨。

英文摘要:

We develop a formalism for constructing stochastic upper bounds on the expected full sample risk for supervised classification tasks via the Hilbert coresets approach within a transductive framework. We explicitly compute tight and meaningful bounds for complex datasets and complex hypothesis classes such as state-of-the-art deep neural network architectures. The bounds we develop exhibit nice properties: i) the bounds are non-uniform in the hypothesis space, ii) in many practical examples, the bounds become effectively deterministic by appropriate choice of prior and training data-dependent posterior distributions on the hypothesis space, and iii) the bounds become significantly better with increase in the size of the training set. We also lay out some ideas to explore for future research.

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。

↑