Yasaman Bahri
- Computational Mathematics top 10%
- Condensed Matter Physics top 10%
- Advanced Condensed Matter Physics 2
- Artificial Intelligence top 5%
- Gaussian Processes and Bayesian Inference 5
- Stochastic Gradient Optimization Techniques 4
- Machine Learning and Data Classification 4
- Neural Networks and Applications 3
- Adversarial Robustness in Machine Learning 2
-
- Topological Materials and Phenomena 7
- Quantum many-body systems 3
- Co-authors
- Ashvin VishwanathJeffrey PenningtonJascha Sohl‐DicksteinEhud AltmanRonen VoskJaehoon LeeRoman NovakSurya Ganguli
- Journals
- Proceedings of the National Academy of Sciences (1 paper)Nature Communications (1 paper)Physical Review B (2 papers)
- Partner nations
- United StatesUnited KingdomSwitzerland
In The Last Decade
Yasaman Bahri
17 papers receiving 551 citations
Hit Papers
Peers
Comparison fields: 5 of 86
- Computational Mathematics 10
- Statistical and Nonlinear Physics 138
- Condensed Matter Physics 96
- Artificial Intelligence 254
- Atomic and Molecular Physics, and Optics 237
Countries citing papers authored by Yasaman Bahri
This map shows the geographic impact of Yasaman Bahri'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 Yasaman Bahri with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Yasaman Bahri more than expected).
Fields of papers citing papers by Yasaman Bahri
This network shows the impact of papers produced by Yasaman Bahri. 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 Yasaman Bahri. The network helps show where Yasaman Bahri may publish in the future.
Co-authorship network
The 23 scholars most cited alongside Yasaman Bahri, 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 | 2025 | 7 | |
| 2 | Explaining neural scaling lawsbreakdown → | 2024 | 49 |
| 3 | 2024 | 1 | |
| 4 | 2020 | 6 | |
| 5 | 2019 | 127 | |
| 6 | Sensitivity and Generalization in Neural Networks: an Empirical Study | 2018 | 18 |
| 7 | Bayesian Convolutional Neural Networks with Many Channels are Gaussian Processes. | 2018 | 5 |
| 8 | Deep Neural Networks as Gaussian Processes | 2018 | 76 |
| 9 | 2018 | 37 | |
| 10 | Geometry of neural network loss surfaces via random matrix theory | 2017 | 22 |
| 11 | 2016 | 35 | |
| 12 | 2015 | 155 | |
| 13 | 2015 | 13 | |
| 14 | 2014 | 1 | |
| 15 | 2014 | 20 | |
| 16 | Detecting Majorana fermions in quasi-1D topological phases using non-local order parameters | 2013 | 2 |
| 17 | 2011 | 1 |
About Yasaman Bahri
Yasaman Bahri is a scholar working on Condensed Matter Physics, Artificial Intelligence and Atomic and Molecular Physics, and Optics, having authored 17 papers that have together received 575 indexed citations. Recurring topics across this work include Topological Materials and Phenomena (7 papers), Gaussian Processes and Bayesian Inference (5 papers), Stochastic Gradient Optimization Techniques (4 papers), Machine Learning and Data Classification (4 papers), Neural Networks and Applications (3 papers), Quantum many-body systems (3 papers), Advanced Condensed Matter Physics (2 papers) and Adversarial Robustness in Machine Learning (2 papers). The work is most often cited by research in Computational Mathematics (10 citations), Statistical and Nonlinear Physics (138 citations) and Condensed Matter Physics (96 citations). Yasaman Bahri has collaborated with scholars based in United States, United Kingdom and Switzerland. Frequent co-authors include Ashvin Vishwanath, Jeffrey Pennington, Jascha Sohl‐Dickstein, Ehud Altman, Ronen Vosk, Jaehoon Lee, Roman Novak, Surya Ganguli, Jonathan Kadmon and Samuel S. Schoenholz. Their work appears in journals such as Proceedings of the National Academy of Sciences, Nature Communications and Physical Review B.
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.