J
Jeffrey Pennington
Researcher at Google
Publications - 84
Citations - 37425
Jeffrey Pennington is an academic researcher from Google. The author has contributed to research in topics: Artificial neural network & Deep learning. The author has an hindex of 32, co-authored 75 publications receiving 28787 citations. Previous affiliations of Jeffrey Pennington include University of Southern California & Princeton University.
Papers
More filters
Proceedings Article
KAMA-NNs: low-dimensional rotation based neural networks
TL;DR: New architectures for feedforward neural networks built from products of learned or random low-dimensional rotations that offer substantial space compression and computational speedups in comparison to the unstructured baselines are presented.
Proceedings ArticleDOI
Synergy and Symmetry in Deep Learning: Interactions between the Data, Model, and Inference Algorithm
Lechao Xiao,Jeffrey Pennington +1 more
TL;DR: This paper analyzes the triplet ( D, M, I ) as an integrated system and identifies important synergies that help mitigate the curse of dimensionality.
Posted Content
Understanding Double Descent Requires a Fine-Grained Bias-Variance Decomposition
Ben Adlam,Jeffrey Pennington +1 more
TL;DR: In this article, an interpretable, symmetric decomposition of the variance into terms associated with the randomness from sampling, initialization, and the labels is presented, and a high-dimensional asymptotic behavior of this decomposition for random feature kernel regression is computed.
Journal ArticleDOI
String theory and water waves
TL;DR: In this article, a remarkable role that an infinite hierarchy of nonlinear differential equations plays in organizing and connecting certain string theories non-perturbatively is uncovered, and several string-like special points arise and are connected.
Journal ArticleDOI
Bäcklund transformations, D-branes and fluxes in minimal type 0 strings
TL;DR: In this paper, the authors studied the properties of the string equations in the (2, 4k) superconformal minimal model backgrounds, focusing on the fully nonperturbative string equations which define the partition function of the model.