Why Do Better Loss Functions Lead to Less Transferable Features?

Simon Kornblith, Ting Chen, Honglak Lee, Mohammad Norouzi 0002. Why Do Better Loss Functions Lead to Less Transferable Features?. In Marc'Aurelio Ranzato, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, Jennifer Wortman Vaughan, editors, Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual. pages 28648-28662, 2021. [doi]

Authors

Simon Kornblith

This author has not been identified. Look up 'Simon Kornblith' in Google

Ting Chen

This author has not been identified. Look up 'Ting Chen' in Google

Honglak Lee

This author has not been identified. Look up 'Honglak Lee' in Google

Mohammad Norouzi 0002

This author has not been identified. Look up 'Mohammad Norouzi 0002' in Google