 A Signal Propagation Perspective for Pruning Neural Networks at
InitializationInternational Conference on Learning Representations (ICLR), 2019 |
 The Normalization Method for Alleviating Pathological Sharpness in Wide
Neural NetworksNeural Information Processing Systems (NeurIPS), 2019 |
 A Mean Field Theory of Quantized Deep Networks: The Quantization-Depth
Trade-OffNeural Information Processing Systems (NeurIPS), 2019 |
 Infinitely deep neural networks as diffusion processesInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2019 |
 Dynamical Isometry is Achieved in Residual Networks in a Universal Way
for any Activation FunctionInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2018 |
