SS

Samuel S. Schoenholz

0000-0003-1909-9226

cs.LGstat.MLcond-mat.softcond-mat.mtrl-scicond-mat.dis-nncs.AIphysics.comp-phcs.CVcs.NEmachine learning

On Valency

published · living versions

Identifying structural flow defects in disordered solids using machine learning methods

with Ekin D. Cubuk, Jennifer M. Rieser, Brad D. Malone, Joerg Rottler +3

1 version

W_y25n99c2v1 · current

Preprints & journals

54 papers in the corpus · 2012–2024

Force-Field Optimization by End-to-End Differentiable Atomistic Simulation.

Gangan, Abhijeet Sadashiv, Cubuk, Ekin Dogus, Schoenholz, Samuel S et al.

6 citations

404720082025Journal of chemical theory and computation. 2025;21(12):5867-5879

GPT-4o System Card

OpenAI: Aaron Hurst, Adam Lerer, Adam P. Goucher et al.

179 citations

2410.21276v12024arXiv

Programming patchy particles for materials assembly design.

King, Ella M, Du, Chrisy Xiyu, Zhu, Qian-Ze et al.

25 citations

389138912024Proceedings of the National Academy of Sciences of the United States of America. 2024;121(27):e2311891121

Inferring interaction potentials from stochastic particle trajectories

Ella M. King, Megan C. Engel, Caroline Martin et al.

1 citation

2406.01522v12024arXiv

Scaling deep learning for materials discovery.

Merchant, Amil, Batzner, Simon, Schoenholz, Samuel S et al.

1,500 citations

380307202023Nature. 2023;624(7990):80-85

Learning molecular dynamics: predicting the dynamics of glasses by a machine learning simulator.

Liu, Han, Huang, Zijie, Schoenholz, Samuel S et al.

19 citations

373824132023Materials horizons. 2023;10(9):3416-3428

What does a deep neural network confidently perceive? The effective dimension of high certainty class manifolds and their low confidence boundaries

Stanislav Fort, Ekin Dogus Cubuk, Surya Ganguli et al.

0 citations

2210.05546v12022arXiv

Deep equilibrium networks are sensitive to initialization statistics

Atish Agarwala, Samuel S. Schoenholz

0 citations

2207.09432v12022arXiv

Fast Finite Width Neural Tangent Kernel

Roman Novak, Jascha Sohl-Dickstein, Samuel S. Schoenholz

18 citations

2206.08720v12022arXiv

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao et al.

569 citations

2206.04615v32022Transactions on Machine Learning Research, May/2022, https://openreview.net/forum?id=uyTL5Bvosj

Gradients are Not All You Need

Luke Metz, C. Daniel Freeman, Samuel S. Schoenholz et al.

27 citations

2111.05803v22021arXiv

Rapid training of deep neural networks without skip connections or normalization layers using Deep Kernel Shaping

James Martens, Andy Ballard, Guillaume Desjardins et al.

2 citations

2110.01765v12021arXiv

Learn2Hop: Learned Optimization on Rough Landscapes

Amil Merchant, Luke Metz, Sam Schoenholz et al.

2 citations

2107.09661v12021arXiv

dPV: An End-to-End Differentiable Solar-Cell Simulator

Sean Mann, Eric Fadel, Samuel S. Schoenholz et al.

15 citations

2105.06305v32021arXiv

Designing self-assembling kinetics with differentiable statistical physics models.

Goodrich, Carl P, King, Ella M, Schoenholz, Samuel S et al.

67 citations

336539602021Proceedings of the National Academy of Sciences of the United States of America. 2021;118(10)

Tilting the playing field: Dynamical loss functions for machine learning

Miguel Ruiz-Garcia, Ge Zhang, Samuel S. Schoenholz et al.

7 citations

2102.03793v32021arXiv

Self-assembling kinetics: Accessing a new design space via differentiable statistical-physics models

Carl P. Goodrich, Ella M. King, Samuel S. Schoenholz et al.

2 citations

2010.15175v22020arXiv

Unifying framework for strong and fragile liquids via machine learning: a study of liquid silica

Ekin D. Cubuk, Andrea J. Liu, Efthimios Kaxiras et al.

6 citations

2008.09681v12020arXiv

Whitening and second order optimization both make information in the dataset unusable during training, and can reduce or prevent generalization

Neha S. Wadia, Daniel Duckworth, Samuel S. Schoenholz et al.

3 citations

2008.07545v42020arXiv

Finite Versus Infinite Neural Networks: an Empirical Study

Jaehoon Lee, Samuel S. Schoenholz, Jeffrey Pennington et al.

79 citations

2007.15801v22020arXiv

On the infinite width limit of neural networks with a standard parameterization

Jascha Sohl-Dickstein, Roman Novak, Samuel S. Schoenholz et al.

24 citations

2001.07301v32020arXiv

Disentangling Trainability and Generalization in Deep Neural Networks

Lechao Xiao, Jeffrey Pennington, Samuel S. Schoenholz

37 citations

1912.13053v22019arXiv

JAX, M.D.: A Framework for Differentiable Physics

Samuel S. Schoenholz, Ekin D. Cubuk

132 citations

1912.04232v22019Advances in Neural Information Processing Systems 33 (2020)

Neural Tangents: Fast and Easy Infinite Neural Networks in Python

Roman Novak, Lechao Xiao, Jiri Hron et al.

100 citations

1912.02803v12019arXiv

A Mean Field Theory of Batch Normalization

Greg Yang, Jeffrey Pennington, Vinay Rao et al.

84 citations

1902.08129v22019arXiv

Dynamical Isometry and a Mean Field Theory of LSTMs and GRUs

Dar Gilboa, Bo Chang, Minmin Chen et al.

23 citations

1901.08987v22019arXiv

Heterogeneous Activation, Local Structure, and Softness in Supercooled Colloidal Liquids.

Ma, Xiaoguang, Davidson, Zoey S, Still, Tim et al.

65 citations

307202952019Physical review letters. 2019;122(2):028001

Machine learning determination of atomic dynamics at grain boundaries.

Sharp, Tristan A, Thomas, Spencer L, Cubuk, Ekin D et al.

100 citations

303017942018Proceedings of the National Academy of Sciences of the United States of America. 2018;115(43):10943-10947

Peptide-Spectra Matching from Weak Supervision

Samuel S. Schoenholz, Sean Hackett, Laura Deming et al.

10 citations

1808.06576v22018arXiv

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 et al.

166 citations

1806.05393v22018arXiv

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

Minmin Chen, Jeffrey Pennington, Samuel S. Schoenholz

70 citations

1806.05394v22018arXiv

The Emergence of Spectral Universality in Deep Networks

Jeffrey Pennington, Samuel S. Schoenholz, Surya Ganguli

88 citations

1802.09979v12018arXiv

Adversarial Spheres

Justin Gilmer, Luke Metz, Fartash Faghri et al.

124 citations

1801.02774v32018arXiv

Mean Field Residual Networks: On the Edge of Chaos

Greg Yang, Samuel S. Schoenholz

74 citations

1712.08969v12017arXiv

Structure-property relationships from universal signatures of plasticity in disordered solids.

Cubuk, E D, Ivancic, R J S, Schoenholz, S S et al.

321 citations

291702312018Science (New York, N.Y.). 2017;358(6366):1033-1037

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

Jeffrey Pennington, Samuel S. Schoenholz, Surya Ganguli

151 citations

1711.04735v12017arXiv

Intriguing Properties of Adversarial Examples

Ekin D. Cubuk, Barret Zoph, Samuel S. Schoenholz et al.

58 citations

1711.02846v12017arXiv

Deep Neural Networks as Gaussian Processes

Jaehoon Lee, Yasaman Bahri, Roman Novak et al.

602 citations

1711.00165v32017arXiv

A Correspondence Between Random Neural Networks and Statistical Field Theory

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

14 citations

1710.06570v12017arXiv

Prediction Errors of Molecular Machine Learning Models Lower than Hybrid DFT Error.

Faber, Felix A, Hutchison, Luke, Huang, Bing et al.

645 citations

289262322018Journal of chemical theory and computation. 2017;13(11):5255-5264

Combining Machine Learning and Physics to Understand Glassy Systems

Samuel S. Schoenholz

20 citations

1709.08015v12017arXiv

Disconnecting structure and dynamics in glassy thin films.

Sussman, Daniel M, Schoenholz, Samuel S, Cubuk, Ekin D et al.

93 citations

289281472018Proceedings of the National Academy of Sciences of the United States of America. 2017;114(40):10601-10605

Neural Message Passing for Quantum Chemistry

Justin Gilmer, Samuel S. Schoenholz, Patrick F. Riley et al.

5,064 citations

1704.01212v22017arXiv

Relationship between local structure and relaxation in out-of-equilibrium glassy systems.

Schoenholz, Samuel S, Cubuk, Ekin D, Kaxiras, Efthimios et al.

125 citations

280282172018Proceedings of the National Academy of Sciences of the United States of America. 2017;114(2):263-267

Deep Information Propagation

Samuel S. Schoenholz, Justin Gilmer, Surya Ganguli et al.

90 citations

1611.01232v22016arXiv

Structural Properties of Defects in Glassy Liquids.

Cubuk, Ekin D, Schoenholz, Samuel S, Kaxiras, Efthimios et al.

77 citations

270927162018The journal of physical chemistry. B. 2016;120(26):6139-46

Strain fluctuations and elastic moduli in disordered solids.

Sussman, Daniel M, Schoenholz, Samuel S, Xu, Ye et al.

7 citations

263824062015Physical review. E, Statistical, nonlinear, and soft matter physics. 2015;92(2):022307

A structural approach to relaxation in glassy liquids

Samuel S. Schoenholz, Ekin D. Cubuk, Daniel M. Sussman et al.

465 citations

1506.07772v32015arXiv

Identifying structural flow defects in disordered solids using machine-learning methods.

Cubuk, E D, Schoenholz, S S, Rieser, J M et al.

448 citations

258159672015Physical review letters. 2015;114(10):108001

Understanding plastic deformation in thermal glasses from single-soft-spot dynamics

Samuel S. Schoenholz, Andrea J. Liu, Robert A. Riggleman et al.

61 citations

1404.1403v12014arXiv

Career total: 91 works. 54 are in this corpus.Showing the 50 most recent.

Profile built from the corpus for this byline.

91

works

12.9K

citations

37

h-index

Corpus papers per year

Author records are still filling in while the Hub is in beta. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.