Sam Schoenholz
Impact in
-
- Model Reduction and Neural Networks
- Statistical Mechanics and Entropy
Papers in
-
- Neural Networks and Applications 2
- Stochastic Gradient Optimization Techniques 1
- Adversarial Robustness in Machine Learning 1
-
- Various Chemistry Research Topics 1
- Co-authors
- Yasaman Bahri (1 shared paper)Jeffrey Pennington (1 shared paper)Surya Ganguli (1 shared paper)Jascha Sohl‐Dickstein (1 shared paper)Jonathan Kadmon (1 shared paper)Alcherio Martinoli (1 shared paper)Ádám Halász (1 shared paper)Ekin D. Cubuk (1 shared paper)
- Journals
- Annual Review of Condensed Matter Physics (1 paper)Nature Physics (1 paper)Physical Review Research (1 paper)Infoscience (Ecole Polytechnique Fédérale de Lausanne) (1 paper)International Conference on Learning Representations (1 paper)
- Partner nations
- United StatesUnited KingdomFrance
In The Last Decade
Sam Schoenholz
6 papers receiving 142 citations
Peers
Comparison fields: 5 of 59
- Computational Mathematics 2
- Statistical and Nonlinear Physics 40
- Artificial Intelligence 79
- Cognitive Neuroscience 22
- Condensed Matter Physics 14
Countries citing papers authored by Sam Schoenholz
This map shows the geographic impact of Sam Schoenholz's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Sam Schoenholz with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Sam Schoenholz more than expected).
Fields of papers citing papers by Sam Schoenholz
This network shows the impact of papers produced by Sam Schoenholz. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Sam Schoenholz. The network helps show where Sam Schoenholz may publish in the future.
Co-authors
The 25 scholars most cited alongside Sam Schoenholz, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.
All Works
| # | Work | ||
|---|---|---|---|
| 1 | 2019 | 131 | |
| 2 | 2009 | 9 | |
| 3 | Fast machine learning models of electronic and energetic properties consistently reach approximation errors better than DFT accuracy | 2017 | 5 |
| 4 | Phonons in pristine and imperfect two-dimensional soft colloidal crystals | 2012 | 1 |
| 5 | Deep Mean Field Theory: Layerwise Variance and Width Variation as Methods to Control Gradient Explosion | 2018 | 1 |
| 6 | 2020 | 1 | |
| 7 | 2025 | 0 |
About Sam Schoenholz
Sam Schoenholz is a scholar working on Artificial Intelligence, Physical and Theoretical Chemistry, Materials Chemistry, Computer Networks and Communications and Molecular Biology, having authored 7 papers that have together received 148 indexed citations. Recurring topics across this work include Neural Networks and Applications (2 papers), Stochastic Gradient Optimization Techniques (1 paper), Adversarial Robustness in Machine Learning (1 paper), Statistical Mechanics and Entropy (1 paper), Distributed Control Multi-Agent Systems (1 paper), Various Chemistry Research Topics (1 paper), Protein Structure and Dynamics (1 paper) and Computational Drug Discovery Methods (1 paper). The work is most often cited by research in Computational Mathematics (2 citations), Statistical and Nonlinear Physics (40 citations), Artificial Intelligence (79 citations), Cognitive Neuroscience (22 citations) and Condensed Matter Physics (14 citations). Sam Schoenholz has collaborated with scholars based in United States, United Kingdom and France. Frequent co-authors include Yasaman Bahri, Jeffrey Pennington, Surya Ganguli, Jascha Sohl‐Dickstein, Jonathan Kadmon, Alcherio Martinoli, Ádám Halász, Ekin D. Cubuk, M. Ani Hsieh and Felix A. Faber. Their work appears in journals such as Annual Review of Condensed Matter Physics, Nature Physics, Physical Review Research, Infoscience (Ecole Polytechnique Fédérale de Lausanne) and International Conference on Learning Representations.
Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.