arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.12868cs.LOcs.LG
收藏

一种通过全局优化的构造性类型理论回归方法

A Constructive, Type-Theoretic Approach to Regression via Global Optimisation

University of Birmingham(伯明翰大学)

Dan R. Ghica, Todd Waugh Ambridge

摘要:

我们研究之间的连接确定性,完整的,和一般的全局优化连续函数和一般概念的回归建设性的类型论的角度通过“可搜索性”的概念。我们看到全局优化的收敛性是可搜索性的直接结果。抽象的设置,使我们能够概括的可搜索性和连续性,高阶函数,使我们可以制定新的收敛准则回归,来自全局优化的收敛。所有理论和激励示例都在证明助手Agda中完全形式化。

英文摘要:

We examine the connections between deterministic, complete, and general global optimisation of continuous functions and a general concept of regression from the perspective of constructive type theory via the concept of 'searchability'. We see how the property of convergence of global optimisation is a straightforward consequence of searchability. The abstract setting allows us to generalise searchability and continuity to higher-order functions, so that we can formulate novel convergence criteria for regression, derived from the convergence of global optimisation. All the theory and the motivating examples are fully formalised in the proof assistant Agda.

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。

↑