Publications

2022
A. Canatar, E. Peters, C. Pehlevan, S. M. Wild, and R. Shaydulin, “Bandwidth Enables Generalization in Quantum Kernel Models ,” arXiv preprint arXiv:2206.06686 , 2022.
P. Masset*, J. A. Zavatone-Veth*, P. J. Connor, V. Murthy#, and C. Pehlevan#, “Population geometry enables fast sampling in spiking neural networks,” biorXiv 10.1101/2022.06.03.494680, 2022.
A. Lin, et al., “Functional imaging and quantification of multi-neuronal olfactory responses in C. elegans,” biorXiv 10.1101/2022.05.27.493772, 2022.
B. Bordelon and C. Pehlevan, “Self-Consistent Dynamical Field Theory of Kernel Evolution in Wide Neural Networks ,” arXiv preprint arXiv:2205.09653, 2022.
J. A. Zavatone-Veth, W. L. Tong, and C. Pehlevan, “Contrasting random and learned features in deep Bayesian linear regression,” Physical Review E, vol. 105, no. 6, pp. 064118, 2022. PDF
J. A. Zavatone-Veth and C. Pehlevan, “On neural network kernels and the storage capacity problem,” Neural Computation, vol. 34, no. 5, pp. 1136-1142, 2022. PDF
A. Atanasov*, B. Bordelon*, and C. Pehlevan, “Neural Networks as Kernel Learners: The Silent Alignment Effect,” in International Conference on Learning Representations (ICLR), 2022. PDF
M. Farrell*, B. Bordelon*, S. Trivedi, and C. Pehlevan, “Capacity of Group-invariant Linear Readouts from Equivariant Representations: How Many Objects can be Linearly Classified Under All Possible Views?” in International Conference on Learning Representations (ICLR), 2022. PDF
B. Bordelon and C. Pehlevan, “Learning Curves for Stochastic Gradient Descent on Structured Features,” in International Conference on Learning Representations (ICLR), 2022. PDF
2021
J. A. Zavatone-Veth and C. Pehlevan, “Depth induces scale-averaging in overparameterized linear Bayesian neural networks,” in 55th Asilomar Conference on Signals, Systems, and Computers, 2021. PDF
J. A. Zavatone-Veth and C. Pehlevan, “Exact marginal prior distributions of finite Bayesian neural networks,” in Advances in Neural Information Processing Systems (NeurIPS), (Spotlight), 2021. PDF
J. A. Zavatone-Veth, A. Canatar, B. Ruben, and C. Pehlevan, “Asymptotics of representation learning in finite Bayesian networks,” in Advances in Neural Information Processing Systems (NeurIPS), 2021. PDF
A. Canatar, B. Bordelon, and C. Pehlevan, “Out-of-Distribution Generalization in Kernel Regression,” in Advances in Neural Information Processing Systems (NeurIPS), 2021. PDF
T. Bricken and C. Pehlevan, “Attention approximates Sparse Distributed Memory,” in Advances in Neural Information Processing Systems (NeurIPS), 2021. PDF
N. M. Chapochnikov, C. Pehlevan, and D. B. Chklovskii, “Normative and mechanistic model of an adaptive circuit for efficient encoding and feature extraction,” biorXiv, 2021.
S. Qin, S. Farashahi, D. Lipshutz, A. M. Sengupta, D. B. Chklovskii, and C. Pehlevan, “Coordinated drift of receptive fields during noisy representation learning,” biorXiv 10.1101/2021.08.30.458264, 2021.
B. Bordelon and C. Pehlevan, “Population Codes Enable Learning from Few Examples By Shaping Inductive Bias,” biorXiv 10.1101/2021.03.30.437743v1, 2021.
J. Zavatone-Veth and C. Pehlevan, “Activation function dependence of the storage capacity of treelike neural networks,” Physical Review E, vol. 103, pp. L020301, 2021. PDF
A. Canatar, B. Bordelon, and C. Pehlevan, “Spectral Bias and Task-Model Alignment Explain Generalization in Kernel Regression and Infinitely Wide Neural Networks,” Nature Communications, vol. 12, pp. 2914 , 2021. PDF
K. Vogt, et al., “Internal state configures olfactory behavior and early sensory processing in Drosophila larva,” Science Advances, vol. 7, no. 1, pp. eabd6900, 2021. PDF

Pages