World's Best Scientists 2026 revealed!
Samuel S. Schoenholz

Samuel S. Schoenholz

Overview

Samuel S. Schoenholz is a researcher affiliated with OpenAI in the United States, specializing in interdisciplinary fields involving computer science, materials science, and physics and astronomy. Their work primarily explores intersections between machine learning and physical sciences.

The scientist has contributed extensively to the study of advanced neural networks and their applications, particularly in materials science and physics. Their research themes include machine learning in materials science, advanced neural network applications, and theoretical and computational physics. Further topics covered by their work include material dynamics and properties, advanced thermodynamics and statistical mechanics, as well as protein structure and dynamics.

Frequent co-authors in their body of work include Ekin D. Cubuk, Jascha Sohl-Dickstein, Ella M. King, Michael P. Brenner, and Mathieu Bauchy. Collaboration with these researchers has contributed to the development and dissemination of their research findings.

Samuel S. Schoenholz has published in various scientific venues, with repeated contributions to arXiv (Cornell University), Proceedings of the National Academy of Sciences, Nature, Nature Physics, and the Journal of Statistical Mechanics Theory and Experiment.

Notable recent papers include:

  • Scaling deep learning for materials discovery (2023), published in Nature
  • Unveiling the predictive power of static structure in glassy systems (2020), published in Nature Physics
  • Designing self-assembling kinetics with differentiable statistical physics models (2021), published in Proceedings of the National Academy of Sciences
  • Finite Versus Infinite Neural Networks: an Empirical Study (2020), published in arXiv (Cornell University)
  • JAX, M.D. A framework for differentiable physics* (2021), published in Journal of Statistical Mechanics Theory and Experiment

Best Publications

  • Neural Message Passing for Quantum Chemistry

    Justin Gilmer;Samuel S. Schoenholz;Patrick F. Riley;Oriol Vinyals

  • Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent

    Jaehoon Lee;Lechao Xiao;Samuel S. Schoenholz;Yasaman Bahri

  • Deep Neural Networks as Gaussian Processes

    Jaehoon Lee;Yasaman Bahri;Roman Novak;Samuel S. Schoenholz

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

    Felix A. Faber;Luke Hutchison;Bing Huang;Justin Gilmer

  • Unveiling the predictive power of static structure in glassy systems

    V. Bapst;T. Keck;A. Grabska-Barwińska;C. Donner

  • Statistical Mechanics of Deep Learning

    Yasaman Bahri;Jonathan Kadmon;Jeffrey Pennington;Sam S. Schoenholz

  • 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 S. Schoenholz

  • Deep Information Propagation

    Samuel S. Schoenholz;Justin Gilmer;Surya Ganguli;Jascha Sohl-Dickstein

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

    Jeffrey Pennington;Samuel S. Schoenholz;Surya Ganguli

  • Mean Field Residual Networks: On the Edge of Chaos

    Greg Yang;Samuel S. Schoenholz

  • A Mean Field Theory of Batch Normalization

    Greg Yang;Jeffrey Pennington;Vinay Rao;Jascha Sohl-Dickstein

  • The Emergence of Spectral Universality in Deep Networks

    Jeffrey Pennington;Samuel S. Schoenholz;Surya Ganguli

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

    Minmin Chen;Jeffrey Pennington;Samuel S. Schoenholz

  • Neural Tangents: Fast and Easy Infinite Neural Networks in Python

    Roman Novak;Lechao Xiao;Jiri Hron;Jaehoon Lee

  • Machine learning determination of atomic dynamics at grain boundaries.

    Tristan A. Sharp;Spencer L. Thomas;Ekin D. Cubuk;Samuel S. Schoenholz

  • Adversarial Spheres.

    Justin Gilmer;Luke Metz;Fartash Faghri;Samuel S. Schoenholz

  • Finite Versus Infinite Neural Networks: an Empirical Study

    Jaehoon Lee;Samuel S. Schoenholz;Jeffrey Pennington;Ben Adlam

  • Intriguing Properties of Adversarial Examples

    Ekin Dogus Cubuk;Barret Zoph;Samuel Stern Schoenholz;Quoc V. Le

  • JAX MD: A Framework for Differentiable Physics

    Samuel S. Schoenholz;Ekin Dogus Cubuk

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

    Samuel S. Schoenholz;Ekin D. Cubuk

Frequent Co-Authors

Ekin D. Cubuk
Ekin D. Cubuk Google (United States)
Jascha Sohl-Dickstein
Jascha Sohl-Dickstein Google (United States)
Arjun G. Yodh
Arjun G. Yodh University of Pennsylvania
Surya Ganguli
Surya Ganguli Stanford University
Efthimios Kaxiras
Efthimios Kaxiras Harvard University
George E. Dahl
George E. Dahl Google (United States)
Oriol Vinyals
Oriol Vinyals DeepMind (United Kingdom)
Douglas J. Durian
Douglas J. Durian University of Pennsylvania
Sidney R. Nagel
Sidney R. Nagel University of Chicago
Michael P. Brenner
Michael P. Brenner University of Michigan–Ann Arbor

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Exploring computer science doesn’t have to be limited to on-campus options. For students looking for flexibility, accelerated studies, or affordability, several related online degrees can help you carve out a rewarding tech or engineering career.

One popular choice is an online computer science degree. These programs are ideal for those seeking a fast-track to high-demand roles in software development, data analytics, or cybersecurity. Aspiring engineers may also consider an online environmental engineering degree science and engineering pathway, which paves the way for impactful careers addressing global environmental challenges.

Cost is often a key consideration. If budget is top of mind, research the mechanical engineering cost of education to find affordable, accredited courses that fit your needs. Alternatively, those interested in physics can pursue a bachelor of science in physics online, opening doors to diverse roles in research, education, and engineering.

Online degrees offer flexibility, lower costs, and a range of career pathways—making them an excellent option for future computer science and STEM professionals.

Best Scientists Citing Samuel S. Schoenholz

Trending Scientists

Recently Published Articles