Decoupled Classifiers for Group-Fair and Efficient Machine Learning

Explore a thought-provoking conference talk from FAT* 2018 that delves into the concept of decoupled classifiers for achieving group-fair and efficient machine learning. Presented by Nicole Immorlica, in collaboration with Cynthia Dwork, Adam Tauman Kalai, and Mark DM Leiserson, this 20-minute presentation examines innovative approaches to addressing fairness and efficiency in ML systems. Gain insights into the researchers' proposed methods for developing classifiers that promote group fairness while maintaining computational efficiency. Understand the implications of their work for creating more equitable and effective machine learning models across various applications. Access the full conference program and related research paper to deepen your understanding of this crucial topic in the field of fair, accountable, and transparent machine learning.

FAT* 2018: Nicole Immorlica - Decoupled Classifiers for Group-Fair and Efficient Machine Learning