Author of the publication

copy delete add this publication to your clipboard
community post
history of this post
URL
DOI
BibTeX
EndNote
APA
Chicago
DIN 1505
Harvard
MSOffice XML

Identifying and attacking the saddle point problem in high-dimensional non-convex optimization

Y. Dauphin, R. Pascanu, C. Gulcehre, K. Cho, S. Ganguli, and Y. Bengio. (2014)cite arxiv:1406.2572Comment: The theoretical review and analysis in this article draw heavily from arXiv:1405.4604 cs.LG.

Please choose a person to relate this publication to

To differ between persons with the same name, the academic degree and the title of an important publication will be displayed. You can also use the button next to the name to display some publications already assigned to the person.

Indranil Ganguli

Arnab Ganguli

Gusti Ngurah Agung Suryaputra

Surya Hermawan

Djoenaidy Suryatanto

Other publications of authors with the same name

Fundamental bounds on the fidelity of sensory cortical coding.O. Rumyantsev, J. Lecoq, O. Hernandez, Y. Zhang, J. Savall, R. Chrapkiewicz, J. Li, H. Zeng, S. Ganguli, and M. Schnitzer. Nat., 580 (7801): 100-105 (2020)Short-term memory in neuronal networks through dynamical compressed sensing.S. Ganguli, and H. Sompolinsky. NIPS, page 667-675. Curran Associates, Inc., (2010)Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel.S. Fort, G. Dziugaite, M. Paul, S. Kharaghani, D. Roy, and S. Ganguli. NeurIPS, (2020)Identifying Learning Rules From Neural Network Observables.A. Nayebi, S. Srivastava, S. Ganguli, and D. Yamins. NeurIPS, (2020)Pruning neural networks without any data by iteratively conserving synaptic flow.H. Tanaka, D. Kunin, D. Yamins, and S. Ganguli. NeurIPS, (2020)Reverse engineering recurrent networks for sentiment classification reveals line attractor dynamics.N. Maheswaranathan, A. Williams, M. Golub, S. Ganguli, and D. Sussillo. NeurIPS, page 15670-15679. (2019)A theory of high dimensional regression with arbitrary correlations between input features and target functions: sample complexity, multiple descent curves and a hierarchy of phase transitions.G. Mel, and S. Ganguli. ICML, volume 139 of Proceedings of Machine Learning Research, page 7578-7587. PMLR, (2021)Emergent properties of the local geometry of neural loss landscapesS. Fort, and S. Ganguli. (2019)cite arxiv:1910.05929Comment: 10 pages, 8 figures.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, and S. Ganguli. CoRR, (2024)Exact solutions to the nonlinear dynamics of learning in deep linear neural networks.A. Saxe, J. McClelland, and S. Ganguli. ICLR, (2014)

BibSonomy

Disambiguation of "Ganguli, Surya"

copy delete add this publication to your clipboard
community post
history of this post
URL
DOI
BibTeX
EndNote
APA
Chicago
DIN 1505
Harvard
MSOffice XML

Identifying and attacking the saddle point problem in high-dimensional non-convex optimization

Please choose a person to relate this publication to

Indranil Ganguli

Arnab Ganguli

Gusti Ngurah Agung Suryaputra

Surya Hermawan

Djoenaidy Suryatanto

Other publications of authors with the same name

Disambiguation

BibSonomy

Disambiguation of "Ganguli, Surya"

copydeleteadd this publication to your clipboardcommunity posthistory of this postURLDOIBibTeXEndNoteAPAChicagoDIN 1505HarvardMSOffice XML Identifying and attacking the saddle point problem in high-dimensional non-convex optimization

Please choose a person to relate this publication to

Indranil Ganguli

Arnab Ganguli

Gusti Ngurah Agung Suryaputra

Surya Hermawan

Djoenaidy Suryatanto

Other publications of authors with the same name

Disambiguation

copy delete add this publication to your clipboard
community post
history of this post
URL
DOI
BibTeX
EndNote
APA
Chicago
DIN 1505
Harvard
MSOffice XML

Identifying and attacking the saddle point problem in high-dimensional non-convex optimization