Boris Hanin

Cited by

	All	Since 2019
Citations	3516	3412
h-index	21	19
i10-index	29	27

940

470

235

705

20162017201820192020202120222023202413 16 43 173 345 453 600 896 921

Public access

View all

19 articles

0 articles

available

not available

Based on funding mandates

Co-authors

David RolnickMcGill University, Mila Quebec AI InstituteVerified email at cs.mcgill.ca
Guergana PetrovaTexas A&M UniversityVerified email at tamu.edu
Yaiza CanzaniUniversity of North Carolina at Chapel HillVerified email at email.unc.edu
Ronald DeVoreProfessor of Matematics, Texas A&M UniversityVerified email at math.tamu.edu
Mihai NicaUniversity of GuelphVerified email at uoguelph.ca
Sho YaidaFAIR at MetaVerified email at meta.com
Daniel A. RobertsResearch Scientist @ OpenAI, Visiting Scientist @ MITVerified email at mit.edu
Steve ZelditchWayne and Elizabeth Jones Professor of Mathematics, Northwestern UniversityVerified email at math.northwestern.edu
Simon FoucartProfessor of Mathematics, Texas A&M UniversityVerified email at tamu.edu
Ingrid DaubechiesDuke UniversityVerified email at math.duke.edu
Mark SellkeAssistant Professor of Statistics, Harvard UniversityVerified email at fas.harvard.edu
Peng ZhouUC Berkeley, Math DepartmentVerified email at berkeley.edu
Yi SunAssistant Professor, UChicago StatisticsVerified email at statistics.uchicago.edu
Zhangyang (Atlas) WangXTX Markets & University of Texas at AustinVerified email at utexas.edu
Wuyang ChenAssistant Professor, CS@Simon Fraser UniversityVerified email at sfu.ca
Grigoris PaourisProfessor in Mathematics, Texas A&M UniversityVerified email at math.tamu.edu
Erik LundbergFlorida Atlantic UniversityVerified email at fau.edu
Leonid HaninIdaho State UniversityVerified email at isu.edu

Boris Hanin

Assistant Professor, Princeton ORFE

Verified email at princeton.edu - Homepage

probability mathematical physics deep learning


Title Sort by citations Sort by year Sort by title	Cited by Cited by	Year
Universal function approximation by deep neural nets with bounded width and relu activations B Hanin Mathematics 7 (10), 992, 2019	442	2019
The principles of deep learning theory DA Roberts, S Yaida, B Hanin Cambridge University Press, 2022	351	2022
Which neural net architectures give rise to exploding and vanishing gradients? B Hanin Advances in neural information processing systems 31, 2018	343	2018
Nonlinear Approximation and (Deep) Networks I Daubechies, R DeVore, S Foucart, B Hanin, G Petrova Constructive Approximation 55 (1), 127-172, 2022	311	2022
How to start training: The effect of initialization and architecture B Hanin, D Rolnick Advances in neural information processing systems 31, 2018	300	2018
Approximating continuous functions by relu nets of minimal width B Hanin, M Sellke arXiv preprint arXiv:1710.11278, 2017	261	2017
Complexity of linear regions in deep networks B Hanin, D Rolnick International Conference on Machine Learning, 2596-2604, 2019	258	2019
Neural network approximation R DeVore, B Hanin, G Petrova Acta Numerica 30, 327-444, 2021	250	2021
Deep relu networks have surprisingly few activation patterns B Hanin, D Rolnick Advances in neural information processing systems 32, 2019	250	2019
Finite depth and width corrections to the neural tangent kernel B Hanin, M Nica arXiv preprint arXiv:1909.05989, 2019	172	2019
Products of many large random matrices and gradients in deep neural networks B Hanin, M Nica Communications in Mathematical Physics 376 (1), 287-322, 2020	86	2020
Scaling limit for the kernel of the spectral projector and remainder estimates in the pointwise Weyl law Y Canzani, B Hanin Analysis & PDE 8 (7), 1707-1731, 2015	46	2015
Random neural networks in the infinite width limit as Gaussian processes B Hanin The Annals of Applied Probability 33 (6A), 4798-4819, 2023	45	2023
Local universality for zeros and critical points of monochromatic random waves Y Canzani, B Hanin Communications in Mathematical Physics 378 (3), 1677-1712, 2020	32	2020
Correlations and pairing between zeros and critical points of Gaussian random polynomials B Hanin International Mathematics Research Notices 2015 (2), 381-421, 2015	31	2015
Pairing of zeros and critical points for random polynomials B Hanin	29	2017
Correlation functions in random fully connected neural networks at finite width B Hanin arXiv preprint arXiv:2204.01058, 2022	25	2022
How data augmentation affects optimization for linear regression B Hanin, Y Sun Advances in neural information processing systems 34, 8095-8105, 2021	24	2021
Nodal sets of random eigenfunctions for the isotropic harmonic oscillator B Hanin, S Zelditch, P Zhou International Mathematics Research Notices 2015 (13), 4813-4839, 2015	24	2015
Bayesian interpolation with deep linear networks B Hanin, A Zlokapa Proceedings of the National Academy of Sciences 120 (23), e2301345120, 2023	23	2023

The system can't perform the operation now. Try again later.

Articles 1–20

Citations per year

Duplicate citations

Merged citations

Add co-authorsCo-authors

Follow

Cited by

Co-authors