The Cram Method for Efficient Simultaneous Learning and Evaluation

• Published in: arXiv.org
• Main Authors: Jia, Zeyang, Imai, Kosuke, Li, Michael Lingzhi
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 11.03.2024
• Subjects: Algorithms; Asymptotic properties; Distance learning; Machine learning; Splitting; Standard error

We introduce the "cram" method, a general and efficient approach to simultaneous learning and evaluation using a generic machine learning (ML) algorithm. In a single pass of batched data, the proposed method repeatedly trains an ML algorithm and tests its empirical performance. Because it...