Daniel Kunin

Cited by

	All	Since 2019
Citations	928	927
h-index	9	9
i10-index	9	9

300

150

225

20192020202120222023202411 36 148 228 294 206

Public access

View all

2 articles

0 articles

available

not available

Based on funding mandates

Co-authors

Surya GanguliAssociate Professor, Stanford UniversityVerified email at stanford.edu
Daniel YaminsAssistant Professor of Computer Science and Psychology, Stanford UniversityVerified email at stanford.edu
Hidenori TanakaGroup Leader, CBS-NTT Program in "Physics of Intelligence", Harvard UniversityVerified email at fas.harvard.edu
Javier Sagastuy-BrenaStanford UniversityVerified email at stanford.edu
Ma ChaoDepartment of Mathematics, Stanford UniversityVerified email at stanford.edu
Lexing YingProfessor of Mathematics, Stanford UniversityVerified email at stanford.edu
Lei Wu (吴磊)Assistant Professor, Peking UniversityVerified email at math.pku.edu.cn
Aleksandrina GoevaUniversity of TorontoVerified email at broadinstitute.org
Cotton SeedBroad Institute of MIT and HarvardVerified email at alum.mit.edu
Aran NayebiICoN Postdoctoral Fellow, MITVerified email at mit.edu
Eshed MargalitStanford UniversityVerified email at stanford.edu
Lauren GillespieComputer Science PhD Student, Stanford UniversityVerified email at cs.stanford.edu

Daniel Kunin

Stanford University

Verified email at stanford.edu - Homepage


Title Sort by citations Sort by year Sort by title	Cited by Cited by	Year
Pruning neural networks without any data by iteratively conserving synaptic flow H Tanaka, D Kunin, DL Yamins, S Ganguli Advances in neural information processing systems 33, 6377-6389, 2020	595	2020
Loss landscapes of regularized linear autoencoders D Kunin, J Bloom, A Goeva, C Seed International conference on machine learning, 3560-3569, 2019	98	2019
Neural mechanics: Symmetry and broken conservation laws in deep learning dynamics D Kunin, J Sagastuy-Brena, S Ganguli, DLK Yamins, H Tanaka arXiv preprint arXiv:2012.04728, 2020	68	2020
Beyond the Quadratic Approximation: the Multiscale Structure of Neural Network Loss Landscapes C Ma, D Kunin, L Wu, L Ying arXiv preprint arXiv:2204.11326, 2022	53*	2022
Two routes to scalable credit assignment without weight symmetry D Kunin, A Nayebi, J Sagastuy-Brena, S Ganguli, J Bloom, D Yamins International Conference on Machine Learning, 5511-5521, 2020	37	2020
Noether’s Learning Dynamics: Role of Symmetry Breaking in Neural Networks H Tanaka, D Kunin	28*	2021
The asymmetric maximum margin bias of quasi-homogeneous neural networks D Kunin, A Yamamura, C Ma, S Ganguli arXiv preprint arXiv:2210.03820, 2022	18	2022
The Limiting Dynamics of SGD: Modified Loss, Phase-Space Oscillations, and Anomalous Diffusion D Kunin, J Sagastuy-Brena, L Gillespie, E Margalit, H Tanaka, S Ganguli, ... Neural Computation 36 (1), 151-174, 2023	17*	2023
Stochastic collapse: How gradient noise attracts sgd dynamics towards simpler subnetworks F Chen, D Kunin, A Yamamura, S Ganguli Advances in Neural Information Processing Systems 36, 2024	13	2024
Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning D Kunin, A Raventós, C Dominé, F Chen, D Klindt, A Saxe, S Ganguli arXiv preprint arXiv:2406.06158, 2024	1	2024
A Quasistatic Derivation of Optimization Algorithms' Exploration on Minima Manifolds C Ma, D Kunin, L Ying

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

Articles 1–11

Citations per year

Duplicate citations

Merged citations

Add co-authorsCo-authors

Follow

Cited by

Co-authors