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

Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent.

J. Lee, L. Xiao, S. Schoenholz, Y. Bahri, R. Novak, J. Sohl-Dickstein, and J. Pennington. NeurIPS, page 8570-8581. (2019)

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.

Jascha Sohl-Dickstein

Jascha Kehr

Jascha Melomedov

Michael Dickstein

Anja Sohl

Other publications of authors with the same name

The large learning rate phase of deep learning: the catapult mechanismA. Lewkowycz, Y. Bahri, E. Dyer, J. Sohl-Dickstein, and G. Gur-Ari. arXiv preprint arXiv:2003.02218, (2020)Towards NNGP-guided Neural Architecture Search.D. Park, J. Lee, D. Peng, Y. Cao, and J. Sohl-Dickstein. CoRR, (2020)Understanding and correcting pathologies in the training of learned optimizers.L. Metz, N. Maheswaranathan, J. Nixon, C. Freeman, and J. Sohl-Dickstein. ICML, volume 97 of Proceedings of Machine Learning Research, page 4556-4565. PMLR, (2019)Unrolled Generative Adversarial Networks.L. Metz, B. Poole, D. Pfau, and J. Sohl-Dickstein. ICLR (Poster), OpenReview.net, (2017)Infinite attention: NNGP and NTK for deep attention networks.J. Hron, Y. Bahri, J. Sohl-Dickstein, and R. Novak. ICML, volume 119 of Proceedings of Machine Learning Research, page 4376-4386. PMLR, (2020)Neural Tangents: Fast and Easy Infinite Neural Networks in Python.R. Novak, L. Xiao, J. Hron, J. Lee, A. Alemi, J. Sohl-Dickstein, and S. Schoenholz. ICLR, OpenReview.net, (2020)Deep Neural Networks as Gaussian Processes.J. Lee, Y. Bahri, R. Novak, S. Schoenholz, J. Pennington, and J. Sohl-Dickstein. ICLR (Poster), OpenReview.net, (2018)Neural Tangents: Fast and Easy Infinite Neural Networks in Python.R. Novak, L. Xiao, J. Hron, J. Lee, A. Alemi, J. Sohl-Dickstein, and S. Schoenholz. CoRR, (2019)Language Model CascadesD. Dohan, W. Xu, A. Lewkowycz, J. Austin, D. Bieber, R. Lopes, Y. Wu, H. Michalewski, R. Saurous, J. Sohl dickstein and 2 other author(s). (2022)cite arxiv:2207.10342Comment: Presented as spotlight at the Beyond Bases workshop at ICML 2022 (https://beyond-bayes.github.io).The Effect of Network Width on Stochastic Gradient Descent and Generalization: an Empirical Study.D. Park, J. Sohl-Dickstein, Q. Le, and S. Smith. ICML, volume 97 of Proceedings of Machine Learning Research, page 5042-5051. PMLR, (2019)

BibSonomy

Disambiguation of "Sohl-Dickstein, Jascha"

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

Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent.

Please choose a person to relate this publication to

Jascha Sohl-Dickstein

Jascha Kehr

Jascha Melomedov

Michael Dickstein

Anja Sohl

Other publications of authors with the same name

Disambiguation

BibSonomy

Disambiguation of "Sohl-Dickstein, Jascha"

copydeleteadd this publication to your clipboardcommunity posthistory of this postURLDOIBibTeXEndNoteAPAChicagoDIN 1505HarvardMSOffice XML Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent.

Please choose a person to relate this publication to

Jascha Sohl-Dickstein

Jascha Kehr

Jascha Melomedov

Michael Dickstein

Anja Sohl

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

Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent.