Adlam, Ben, Jaehoon Lee, Lechao Xiao, Jeffrey Pennington, and Jasper Snoek. 2020.
βExploring the Uncertainty Properties of Neural Networksβ Implicit Priors in the Infinite-Width Limit.β arXiv:2010.07355 [Cs, Stat], October.
Arora, Sanjeev, Simon S Du, Wei Hu, Zhiyuan Li, Russ R Salakhutdinov, and Ruosong Wang. 2019. βOn Exact Computation with an Infinitely Wide Neural Net.β In Advances in Neural Information Processing Systems, 10.
Belkin, Mikhail, Siyuan Ma, and Soumik Mandal. 2018.
βTo Understand Deep Learning We Need to Understand Kernel Learning.β In
International Conference on Machine Learning, 541β49.
Chen, Lin, and Sheng Xu. 2020.
βDeep Neural Tangent Kernel and Laplace Kernel Have the Same RKHS.β arXiv:2009.10683 [Cs, Math, Stat], October.
Chen, Minshuo, Yu Bai, Jason D. Lee, Tuo Zhao, Huan Wang, Caiming Xiong, and Richard Socher. 2021.
βTowards Understanding Hierarchical Learning: Benefits of Neural Representations.β arXiv:2006.13436 [Cs, Stat], March.
Cho, Youngmin, and Lawrence K. Saul. 2009.
βKernel Methods for Deep Learning.β In
Proceedings of the 22nd International Conference on Neural Information Processing Systems, 22:342β50. NIPSβ09. Red Hook, NY, USA: Curran Associates Inc.
Fan, Zhou, and Zhichao Wang. 2020.
βSpectra of the Conjugate Kernel and Neural Tangent Kernel for Linear-Width Neural Networks.β In
Advances in Neural Information Processing Systems, 33:12.
Fort, Stanislav, Gintare Karolina Dziugaite, Mansheej Paul, Sepideh Kharaghani, Daniel M. Roy, and Surya Ganguli. 2020.
βDeep Learning Versus Kernel Learning: An Empirical Study of Loss Landscape Geometry and the Time Evolution of the Neural Tangent Kernel.β In
Advances in Neural Information Processing Systems. Vol. 33.
Gal, Yarin, and Zoubin Ghahramani. 2015.
βDropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning.β In
Proceedings of the 33rd International Conference on Machine Learning (ICML-16).
Geifman, Amnon, Abhay Yadav, Yoni Kasten, Meirav Galun, David Jacobs, and Ronen Basri. 2020.
βOn the Similarity Between the Laplace and Neural Tangent Kernels.β In
arXiv:2007.01580 [Cs, Stat].
Ghahramani, Zoubin. 2013.
βBayesian Non-Parametrics and the Probabilistic Approach to Modelling.β Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences 371 (1984): 20110553.
Girosi, Federico, Michael Jones, and Tomaso Poggio. 1995.
βRegularization Theory and Neural Networks Architectures.β Neural Computation 7 (2): 219β69.
Giryes, R., G. Sapiro, and A. M. Bronstein. 2016.
βDeep Neural Networks with Random Gaussian Weights: A Universal Classification Strategy?β IEEE Transactions on Signal Processing 64 (13): 3444β57.
He, Bobby, Balaji Lakshminarayanan, and Yee Whye Teh. 2020.
βBayesian Deep Ensembles via the Neural Tangent Kernel.β In
Advances in Neural Information Processing Systems. Vol. 33.
Jacot, Arthur, Franck Gabriel, and Clement Hongler. 2018.
βNeural Tangent Kernel: Convergence and Generalization in Neural Networks.β In
Advances in Neural Information Processing Systems, 31:8571β80. NIPSβ18. Red Hook, NY, USA: Curran Associates Inc.
Kristiadi, Agustinus, Matthias Hein, and Philipp Hennig. 2021.
βAn Infinite-Feature Extension for Bayesian ReLU Nets That Fixes Their Asymptotic Overconfidence.β Advances in Neural Information Processing Systems 34: 18789β800.
Lee, Jaehoon, Yasaman Bahri, Roman Novak, Samuel S. Schoenholz, Jeffrey Pennington, and Jascha Sohl-Dickstein. 2018.
βDeep Neural Networks as Gaussian Processes.β In
ICLR.
Lee, Jaehoon, Lechao Xiao, Samuel S. Schoenholz, Yasaman Bahri, Roman Novak, Jascha Sohl-Dickstein, and Jeffrey Pennington. 2019.
βWide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent.β In
Advances in Neural Information Processing Systems, 8570β81.
Matthews, Alexander Graeme de Garis, Mark Rowland, Jiri Hron, Richard E. Turner, and Zoubin Ghahramani. 2018.
βGaussian Process Behaviour in Wide Deep Neural Networks.β In
arXiv:1804.11271 [Cs, Stat].
Meronen, Lassi, Christabella Irwanto, and Arno Solin. 2020.
βStationary Activations for Uncertainty Calibration in Deep Learning.β In
Advances in Neural Information Processing Systems. Vol. 33.
Neal, Radford M. 1996a.
βBayesian Learning for Neural Networks.β Secaucus, NJ, USA: Springer-Verlag New York, Inc.
βββ. 1996b.
βPriors for Infinite Networks.β In
Bayesian Learning for Neural Networks, edited by Radford M. Neal, 29β53. Lecture Notes in Statistics. New York, NY: Springer.
Novak, Roman, Lechao Xiao, Jiri Hron, Jaehoon Lee, Alexander A. Alemi, Jascha Sohl-Dickstein, and Samuel S. Schoenholz. 2019.
βNeural Tangents: Fast and Easy Infinite Neural Networks in Python.β arXiv:1912.02803 [Cs, Stat], December.
Novak, Roman, Lechao Xiao, Jaehoon Lee, Yasaman Bahri, Greg Yang, Jiri Hron, Daniel A. Abolafia, Jeffrey Pennington, and Jascha Sohl-Dickstein. 2020.
βBayesian Deep Convolutional Networks with Many Channels Are Gaussian Processes.β In
The International Conference on Learning Representations.
Pearce, Tim, Russell Tsuchida, Mohamed Zaki, Alexandra Brintrup, and Andy Neely. 2019. βExpressive Priors in Bayesian Neural Networks: Kernel Combinations and Periodic Functions.β In Uncertainty in Artificial Intelligence, 11.
Sachdeva, Noveen, Mehak Preet Dhaliwal, Carole-Jean Wu, and Julian McAuley. 2022.
βInfinite Recommendation Networks: A Data-Centric Approach.β arXiv.
Tancik, Matthew, Pratul P. Srinivasan, Ben Mildenhall, Sara Fridovich-Keil, Nithin Raghavan, Utkarsh Singhal, Ravi Ramamoorthi, Jonathan T. Barron, and Ren Ng. 2020.
βFourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains.β arXiv:2006.10739 [Cs], June.
Williams, Christopher K. I. 1996.
βComputing with Infinite Networks.β In
Proceedings of the 9th International Conference on Neural Information Processing Systems, 295β301. NIPSβ96. Cambridge, MA, USA: MIT Press.
Yang, Greg, and Edward J. Hu. 2020.
βFeature Learning in Infinite-Width Neural Networks.β arXiv:2011.14522 [Cond-Mat], November.
Zhang, Chiyuan, Samy Bengio, Moritz Hardt, Benjamin Recht, and Oriol Vinyals. 2017.
βUnderstanding Deep Learning Requires Rethinking Generalization.β In
Proceedings of ICLR.
No comments yet. Why not leave one?