Why Do Deep Residual Networks Generalize Better than Deep Feedforward Networks? - A Neural Tangent Kernel Perspective

Kaixuan Huang, Yuqing Wang, Molei Tao, Tuo Zhao. Why Do Deep Residual Networks Generalize Better than Deep Feedforward Networks? - A Neural Tangent Kernel Perspective. In Hugo Larochelle, Marc'Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, Hsuan-Tien Lin, editors, Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual. 2020. [doi]

Authors

Kaixuan Huang

This author has not been identified. Look up 'Kaixuan Huang' in Google

Yuqing Wang

This author has not been identified. Look up 'Yuqing Wang' in Google

Molei Tao

This author has not been identified. Look up 'Molei Tao' in Google

Tuo Zhao

This author has not been identified. Look up 'Tuo Zhao' in Google