Jeffrey Pennington

发表

Finite Versus Infinite Neural Networks: an Empirical Study pdf

Jaehoon Lee, Jascha Sohl-Dickstein, Samuel S. Schoenholz, 2020, NeurIPS.

Understanding Double Descent Requires a Fine-Grained Bias-Variance Decomposition pdf

Jeffrey Pennington, Ben Adlam, Jeffrey Pennington, 2020, NeurIPS.

The Dynamics of Signal Propagation in Gated Recurrent Neural Networks

Samuel S. Schoenholz, Jeffrey Pennington, Greg Yang, 2019 .

The Spectrum of the Fisher Information Matrix of a Single-Hidden-Layer Neural Network

Jeffrey Pennington, Pratik Worah, Jeffrey Pennington, 2018, NeurIPS.

Sensitivity and Generalization in Neural Networks: an Empirical Study pdf

Jascha Sohl-Dickstein, Jeffrey Pennington, Roman Novak, 2018, ICLR.

Disentangling Trainability and Generalization in Deep Neural Networks

Samuel S. Schoenholz, Jeffrey Pennington, Lechao Xiao, 2020, ICML.

Dynamical Isometry and a Mean Field Theory of RNNs: Gating Enables Signal Propagation in Recurrent Neural Networks pdf

Samuel S. Schoenholz, Jeffrey Pennington, Minmin Chen, 2018, ICML.

Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practice

Surya Ganguli, Samuel S. Schoenholz, Jeffrey Pennington, 2017, NIPS.

Dynamical Isometry and a Mean Field Theory of LSTMs and GRUs pdf

Samuel S. Schoenholz, Jeffrey Pennington, Greg Yang, 2019, ArXiv.

Training ultra-deep CNNs with critical initialization

Samuel S. Schoenholz, Jeffrey Pennington, Lechao Xiao, 2017 .

Exact posterior distributions of wide Bayesian neural networks pdf

Jascha Sohl-Dickstein, Jeffrey Pennington, Roman Novak, 2020, ArXiv.

Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes

Jaehoon Lee, Jascha Sohl-Dickstein, Jeffrey Pennington, 2018, ICLR.

Correction: Novel findings with reassessment of exome data: implications for validation testing and interpretation of genomic data

Jeffrey Pennington, Mahdi Sarmady, Eric Marsh, 2018, Genetics in Medicine.

A Random Matrix Perspective on Mixtures of Nonlinearities for Deep Learning pdf

Jeffrey Pennington, Ben Adlam, Jake Levinson, 2019, ArXiv.

Semi-Supervised Recursive Autoencoders for Predicting Sentiment Distributions

Jeffrey Pennington, Andrew Y. Ng, Christopher D. Manning, 2011, EMNLP.

Deep Neural Networks as Gaussian Processes pdf

Jaehoon Lee, Jascha Sohl-Dickstein, Samuel S. Schoenholz, 2017, ICLR.

Exploring the Uncertainty Properties of Neural Networks' Implicit Priors in the Infinite-Width Limit pdf

Jaehoon Lee, Jasper Snoek, Jeffrey Pennington, 2020, ICLR.

Estimating the Spectral Density of Large Implicit Matrices

Ryan P. Adams, Jeffrey Pennington, Matthew J. Johnson, 2018, 1802.03451.

Clinical Data Research Network Lessons Learned

Jeffrey Pennington, Ritu Khare, Charles Bailey, 2016, CRI.

A Mean Field Theory of Batch Normalization pdf

Jascha Sohl-Dickstein, Samuel S. Schoenholz, Jeffrey Pennington, 2019, ICLR.

Spherical Random Features for Polynomial Kernels

Sanjiv Kumar, Jeffrey Pennington, Felix X. Yu, 2015, NIPS.

A Correspondence Between Random Neural Networks and Statistical Field Theory pdf

Jascha Sohl-Dickstein, Samuel S. Schoenholz, Jeffrey Pennington, 2017, ArXiv.

Statistical Mechanics of Deep Learning

Surya Ganguli, Jascha Sohl-Dickstein, Samuel S. Schoenholz, 2020, Annual Review of Condensed Matter Physics.

Nonlinear random matrix theory for deep learning

Jeffrey Pennington, Pratik Worah, Jeffrey Pennington, 2019, NIPS.

Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10, 000-Layer Vanilla Convolutional Neural Networks pdf

Jascha Sohl-Dickstein, Samuel S. Schoenholz, Jeffrey Pennington, 2018, ICML.

Bayesian Convolutional Neural Networks with Many Channels are Gaussian Processes pdf

Jaehoon Lee, Jascha Sohl-Dickstein, Jeffrey Pennington, 2018, ArXiv.

Provable Benefit of Orthogonal Initialization in Optimizing Deep Linear Networks pdf

Jeffrey Pennington, Lechao Xiao, Wei Hu, 2020, ICLR.

Wide neural networks of any depth evolve as linear models under gradient descent

Jaehoon Lee, Jascha Sohl-Dickstein, Samuel S. Schoenholz, 2019, NeurIPS.

The Neural Tangent Kernel in High Dimensions: Triple Descent and a Multi-Scale Theory of Generalization

Jeffrey Pennington, Ben Adlam, Jeffrey Pennington, 2020, ICML.

The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks pdf

Jeffrey Pennington, Ben Adlam, Lechao Xiao, 2020, NeurIPS.

Temperature check: theory and practice for training models with softmax-cross-entropy losses pdf

Yann Dauphin, Jeffrey Pennington, Atish Agarwala, 2020, Trans. Mach. Learn. Res..

GloVe: Global Vectors for Word Representation

Jeffrey Pennington, Christopher D. Manning, Richard Socher, 2014, EMNLP.

Disentangling trainability and generalization in deep learning pdf

Samuel S. Schoenholz, Jeffrey Pennington, Lechao Xiao, 2019, ArXiv.

Geometry of Neural Network Loss Surfaces via Random Matrix Theory

Jeffrey Pennington, Yasaman Bahri, Jeffrey Pennington, 2017, ICML.

KAMA-NNs: Low-dimensional Rotation Based Neural Networks

Krzysztof Choromanski, Jeffrey Pennington, Yunhao Tang, 2019, AISTATS.

The Emergence of Spectral Universality in Deep Networks

Surya Ganguli, Samuel S. Schoenholz, Jeffrey Pennington, 2018, AISTATS.

Dynamic Pooling and Unfolding Recursive Autoencoders for Paraphrase Detection

Jeffrey Pennington, Andrew Y. Ng, Christopher D. Manning, 2011, NIPS.

Covariate Shift in High-Dimensional Random Feature Regression pdf

Jeffrey Pennington, Ben Adlam, Nilesh Tripuraneni, 2021, ArXiv.

Finite Versus Infinite Neural Networks: an Empirical Study pdf

Jaehoon Lee, Samuel S. Schoenholz, Jeffrey Pennington, 2020, NeurIPS.

Novel findings with reassessment of exome data: implications for validation testing and interpretation of genomic data

Jeffrey Pennington, Mahdi Sarmady, Bo Zhang, 2018, Genetics in Medicine.

A RANDOM MATRIX PERSPECTIVE

Jeffrey Pennington, Ben Adlam, Jake Levinson, 2019 .