arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.02424cs.LGmath.CT
收藏

机器学习任务的模式语言

A Pattern Language for Machine Learning Tasks

Jump Trading;MIT(麻省理工学院);Quantinuum;Artidis AG

Benjamin Rodatz, Ian Fan, Tuomas Laakkonen, Neil John Ortega, Thomas Hoffmann, Vincent Wang-Mascianica

AI总结:

本文提出一种将机器学习目标函数形式化为等式约束任务的图形数学框架,统一跨领域方法并实现模型无关的行为设计与优化,并通过可端到端最小编辑数据的“操纵器”任务验证其有效性。

摘要:

我们将目标函数的基本数据形式化为学习者复合体上的等式约束。我们称这些约束为“任务”,并研究这种理想化观点:此类任务决定模型行为。我们为任务发展了一种类似流程图的图形数学,使我们能够:(1)为跨领域的机器学习方法提供统一视角;(2)以模型无关的方式设计和优化期望行为;(3)将理论计算机科学的见解引入实用机器学习。作为我们理论框架潜在实际影响的概念验证,我们展示并实现了一种新颖的“操纵器”任务,该任务以最小限度编辑输入数据以使其具有期望属性。我们的模型无关方法端到端地实现了这一目标,无需定制架构、对抗训练、随机采样或对数据的干预,从而实现了能力强、规模小且训练稳定的模型。

英文摘要:

We formalise the essential data of objective functions as equality constraints on composites of learners. We call these constraints "tasks", and we investigate the idealised view that such tasks determine model behaviours. We develop a flowchart-like graphical mathematics for tasks that allows us to; (1) offer a unified perspective of approaches in machine learning across domains; (2) design and optimise desired behaviours model-agnostically; and (3) import insights from theoretical computer science into practical machine learning. As a proof-of-concept of the potential practical impact of our theoretical framework, we exhibit and implement a novel "manipulator" task that minimally edits input data to have a desired attribute. Our model-agnostic approach achieves this end-to-end, and without the need for custom architectures, adversarial training, random sampling, or interventions on the data, hence enabling capable, small-scale, and training-stable models.

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。

↑