Provable Benefit of Orthogonal Initialization in Optimizing Deep Linear Networks - researchr publication related

researchr

You are not signed in
Sign in
Sign up

Wei Hu, Lechao Xiao, Jeffrey Pennington. Provable Benefit of Orthogonal Initialization in Optimizing Deep Linear Networks. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net, 2020. [doi]

The following publications are possibly variants of this publication:

Adversarial robustness of deep neural networks: A survey from a formal verification perspectiveMeng, Mark Huasong, Bai, Guangdong, Teo, Sin Gee, Hou, Zhe, Xiao, Yan, Lin, Yun, Dong, Jin Song. IEEE Transactions on Dependable and Secure Computing, , 2022.

Width Provably Matters in Optimization for Deep Linear Neural NetworksSimon S. Du, Wei Hu. icml 2019: 1655-1664 [doi]

runs on WebDSL