Explore cutting-edge research and insights on model evaluation in this 1-hour 7-minute paper session presented at an Association for Computing Machinery (ACM) conference. Delve into the latest methodologies, techniques, and best practices for assessing the performance and reliability of machine learning and statistical models. Gain valuable knowledge from expert researchers as they discuss their findings, challenges, and proposed solutions in the field of model evaluation. Enhance your understanding of critical aspects such as metrics selection, validation strategies, and robustness testing to improve the accuracy and effectiveness of your own models.
Overview
Syllabus
Paper session 24: Model evaluation
Taught by
ACM FAccT Conference