no code implementations • ICLR 2019 • Chao GAO, jiyi LIU, Yuan YAO, Weizhi Zhu
In particular, we show that a JS-GAN that uses a neural network discriminator with at least one hidden layer is able to achieve the minimax rate of robust mean estimation under Huber's $\epsilon$-contamination model.
no code implementations • ICLR 2019 • Yifei HUANG, Yuan YAO, Weizhi Zhu
A belief persists long in machine learning that enlargement of margins over training data accounts for the resistance of models to overfitting by increasing the robustness.
1 code implementation • 5 Mar 2019 • Chao Gao, Yuan YAO, Weizhi Zhu
Robust scatter estimation is a fundamental task in statistics.
1 code implementation • 8 Oct 2018 • Weizhi Zhu, Yifei HUANG, Yuan YAO
In this paper, we revisit Breiman's dilemma in deep neural networks with recently proposed spectrally normalized margins, from a novel perspective based on phase transitions of normalized margin distributions in training dynamics.
2 code implementations • 4 Oct 2018 • Chao Gao, jiyi LIU, Yuan YAO, Weizhi Zhu
Similar to the derivation of $f$-GANs, we show that these depth functions that lead to statistically optimal robust estimators can all be viewed as variational lower bounds of the total variation distance in the framework of $f$-Learning.