"Quantum Many-Body Physics Calculations with Large Language Models."
H. Pan, N. Mudur, W. Taranto, M. Tikhanovskaya, S. Venugopalan, Y. Bahri, M. Brenner, E. Kim
arxiv: 2403.03154 (2024). Under review at Nature Communications.
"Les Houches Lectures on Deep Learning at Large and Infinite Width."
Y. Bahri, B. Hanin, A. Brossollet, V. Erba, C. Keup, R. Pacelli, J. Simon
arxiv: 2309.01592 (2023). To appear in Journal of Statistical Mechanics: Theory & Experiment.
"Explaining Neural Scaling Laws."
Y. Bahri, E. Dyer, J. Kaplan, J. Lee, U. Sharma
arxiv: 2102.06701. To appear in PNAS.
"Beyond the Imitation Game: Quantifying and Extrapolating the Capabilities of Language Models."
A. Srivastava, et al. (Collaborative benchmark from 100+ institutions.)
Transactions of Machine Learning Research, 2835-8856 (2023).
"The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning."
A. Andreassen, Y. Bahri, B. Neyshabur, R. Roelofs
Transactions on Machine Learning Research, 2835-8856 (2022)
"Statistical Mechanics of Deep Learning."
Y. Bahri, J. Kadmon, J. Pennington, S.S. Schoenholz, J. Sohl-Dickstein, S. Ganguli
Annual Review of Condensed Matter Physics (2020)
"The large learning rate phase of deep learning: the catapult mechanism."
A. Lewkowycz, Y. Bahri, E. Dyer, J. Sohl-Dickstien, G. Gur-Ari
arxiv: 2003.02218 (2020)
"Infinite-attention: NNGP and NTK for deep attention networks."
J. Hron, Y. Bahri, J. Sohl-Dickstien, R. Novak
ICML 2020 (International Conference of Machine Learning)
"Exact Posterior Distributions of Wide Bayesian Neural Networks."
J. Hron, Y. Bahri, R. Novak, J. Pennington, J. Sohl-Dickstein
ICML 2020 Workshop on Uncertainty in Deep Learning
"Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent."
J. Lee*, L. Xiao*, S. S. Schoenholz, Y. Bahri, J. Sohl-Dickstein, J. Pennington
NeurIPS 2019 (Advances in Neural Information Processing Systems)
Also re-published in special edition of Journal of Statistical Mechanics: Theory and Experiment (2020) 124002.
"Bayesian Convolutional Neural Networks with Many Channels are Gaussian Processes."
R. Novak, L. Xiao, J. Lee*, Y. Bahri*, G. Yang, J. Hron, D. Abolafia, J. Pennington, J. Sohl-Dickstein
*Equal contribution
ICLR 2019 (International Conference on Learning Representations)
L. Xiao, Yasaman Bahri, J. Sohl-Dickstein, S.S. Schoenholz, J. Pennington
ICML 2018 (International Conference on Machine Learning)
"Deep Neural Networks as Gaussian Processes."
J. Lee*, Y. Bahri*, R. Novak, S. S. Schoenholz, J. Pennington, J. Sohl-Dickstein
*Equal contribution
ICLR 2018 (International Conference on Learning Representations)
“Sensitivity and Generalization in Neural Networks: an Empirical Study.”
R. Novak, Y. Bahri, D. Abolafia, J. Pennington, J. Sohl-Dickstein
ICLR 2018 (International Conference on Learning Representations)
“Geometry of Neural Network Loss Surfaces via Random Matrix Theory.”
J. Pennington, Y. Bahri
ICML 2017 (International Conference on Machine Learning)
"Phonon analog of topological nodal semimetals."
H. C. Po, Y. Bahri, A. Vishwanath
Phys. Rev. B. 93, 205158 (2016) (Editor's Suggestion)
“Stable non-Fermi-liquid phase of itinerant spin-orbit coupled ferromagnets.”
Y. Bahri, A. C. Potter
Phys. Rev. B 92, 035131 (2015)
“Localization and topology protected quantum coherence at the edge of hot matter.”
Y. Bahri, R. Vosk, E. Altman, A. Vishwanath
Nature Communications 6:7341 (2015)
Y. Bahri, A. Vishwanath
Phys. Rev. B 89, 155135 (2014)