Samuel Schoenholz
10 papers · 2017–2020 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
🗺️ Taxonomy Completionist (18) 🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird 🏆 Keyword Champion (3)
🧭
Keyword Pioneer
💎
Century Club · Bronze
Venues
Top co-authors
Research topics
Machine Learning
(9)
Optimization & Theory · Machine Learning
(9)
Deep Learning
(7)
Architectures
(7)
Optimization & Theory · Deep Learning
(5)
Techniques
(3)
Mathematics & Optimization
(2)
Artificial Intelligence
(1)
Computer Science
(1)
Computer Vision
(1)
Analysis
(1)
Applications
(1)
Core AI · Artificial Intelligence
(1)
Core AI · Computer Vision
(1)
Core Methods
(1)
Keywords
dynamical isometry
(3)
mean field theory
(3)
initialization scheme
(3)
convolutional neural network
(2)
gradient descent
(2)
free probability theory
(2)
vanishing gradient
(2)
neural tangent kernel
(2)
weight initialization
(2)
gaussian process
(1)
recurrent neural network
(1)
neural network optimization
(1)
generalization bound
(1)
gradient flow
(1)
random matrix theory
(1)
batch normalization
(1)
residual network
(1)
singular value distribution
(1)
linear model
(1)
molecular dynamics
(1)
Papers
Disentangling Trainability and Generalization in Deep Neural Networks
ICML 2020
Finite Versus Infinite Neural Networks: an Empirical Study
NeurIPS 2020
JAX MD: A Framework for Differentiable Physics
NeurIPS 2020
MetaInit: Initializing learning by learning to initialize
NeurIPS 2019
Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent
NeurIPS 2019
Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks
ICML 2018
Dynamical Isometry and a Mean Field Theory of RNNs: Gating Enables Signal Propagation in Recurrent Neural Networks
ICML 2018
The emergence of spectral universality in deep networks
AISTATS 2018
Mean Field Residual Networks: On the Edge of Chaos
NeurIPS 2017
Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practice
NeurIPS 2017