Greg Yang
Microsoft Research (United Kingdom)(GB)
Publications by Year
Research Areas
Adversarial Robustness in Machine Learning, Advanced Neural Network Applications, Neural Networks and Applications, Stochastic Gradient Optimization Techniques, Gaussian Processes and Bayesian Inference
Most-Cited Works
- → Scaling Limits of Wide Neural Networks with Weight Sharing: Gaussian Process Behavior, Gradient Independence, and Neural Tangent Kernel Derivation(2019)187 cited
- Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers(2019)
- → Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes(2018)169 cited
- → A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networks(2019)78 cited
- Mean Field Residual Networks: On the Edge of Chaos(2017)
- → A Mean Field Theory of Batch Normalization(2019)53 cited
- → Tensor Programs II: Neural Tangent Kernel for Any Architecture(2020)53 cited