How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks

Etai Littwin, Omid Saremi, Madhu Advani, Vimal Thilak, Preetum Nakkiran, Chen Huang 0001, Joshua M. Susskind. How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks. In Amir Globersons, Lester Mackey, Danielle Belgrave, Angela Fan, Ulrich Paquet, Jakub M. Tomczak, Cheng Zhang 0005, editors, Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, December 10 - 15, 2024. 2024. [doi]

Abstract

Abstract is missing.