Schoenholz, Samuel

9 publications

ICML 2020 Disentangling Trainability and Generalization in Deep Neural Networks Lechao Xiao, Jeffrey Pennington, Samuel Schoenholz

NeurIPS 2020 Finite Versus Infinite Neural Networks: An Empirical Study Jaehoon Lee, Samuel Schoenholz, Jeffrey Pennington, Ben Adlam, Lechao Xiao, Roman Novak, Jascha Sohl-Dickstein

NeurIPS 2020 JAX MD: A Framework for Differentiable Physics Samuel Schoenholz, Ekin Dogus Cubuk

NeurIPS 2019 MetaInit: Initializing Learning by Learning to Initialize Yann N. Dauphin, Samuel Schoenholz

NeurIPS 2019 Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent Jaehoon Lee, Lechao Xiao, Samuel Schoenholz, Yasaman Bahri, Roman Novak, Jascha Sohl-Dickstein, Jeffrey Pennington

ICML 2018 Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks Lechao Xiao, Yasaman Bahri, Jascha Sohl-Dickstein, Samuel Schoenholz, Jeffrey Pennington

ICML 2018 Dynamical Isometry and a Mean Field Theory of RNNs: Gating Enables Signal Propagation in Recurrent Neural Networks Minmin Chen, Jeffrey Pennington, Samuel Schoenholz

NeurIPS 2017 Mean Field Residual Networks: On the Edge of Chaos Ge Yang, Samuel Schoenholz

NeurIPS 2017 Resurrecting the Sigmoid in Deep Learning Through Dynamical Isometry: Theory and Practice Jeffrey Pennington, Samuel Schoenholz, Surya Ganguli