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

Temperature check: theory and practice for training models with softmax-cross-entropy losses.

A. Agarwala, J. Pennington, Y. Dauphin, and S. Schoenholz. CoRR, (2020)

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.

Ludwig Schoenholz

S Hüttelmaier

S Leopold

S Steinlechner

S Bachmann

Other publications of authors with the same name

Explaining the Learning Dynamics of Direct Feedback Alignment.J. Gilmer, C. Raffel, S. Schoenholz, M. Raghu, and J. Sohl-Dickstein. ICLR (Workshop), OpenReview.net, (2017)On the infinite width limit of neural networks with a standard parameterization.J. Sohl-Dickstein, R. Novak, S. Schoenholz, and J. Lee. CoRR, (2020)Fast Finite Width Neural Tangent Kernel.R. Novak, J. Sohl-Dickstein, and S. Schoenholz. ICML, volume 162 of Proceedings of Machine Learning Research, page 17018-17044. PMLR, (2022)Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent.J. Lee, L. Xiao, S. Schoenholz, Y. Bahri, J. Sohl-Dickstein, and J. Pennington. CoRR, (2019)Gradients are Not All You Need.L. Metz, C. Freeman, S. Schoenholz, and T. Kachman. CoRR, (2021)Dynamical Isometry and a Mean Field Theory of LSTMs and GRUs.D. Gilboa, B. Chang, M. Chen, G. Yang, S. Schoenholz, E. Chi, and J. Pennington. CoRR, (2019)Rapid training of deep neural networks without skip connections or normalization layers using Deep Kernel Shaping.J. Martens, A. Ballard, G. Desjardins, G. Swirszcz, V. Dalibard, J. Sohl-Dickstein, and S. Schoenholz. CoRR, (2021)Specialization as an optimal strategy under varying external conditions.M. Hsieh, Á. Halász, E. Cubuk, S. Schoenholz, and A. Martinoli. ICRA, page 1941-1946. IEEE, (2009)Dynamical Isometry and a Mean Field Theory of RNNs: Gating Enables Signal Propagation in Recurrent Neural Networks.M. Chen, J. Pennington, and S. Schoenholz. ICML, volume 80 of Proceedings of Machine Learning Research, page 872-881. PMLR, (2018)Finite Versus Infinite Neural Networks: an Empirical Study.J. Lee, S. Schoenholz, J. Pennington, B. Adlam, L. Xiao, R. Novak, and J. Sohl-Dickstein. NeurIPS, (2020)

BibSonomy

Disambiguation of "Schoenholz, Samuel S."

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

Temperature check: theory and practice for training models with softmax-cross-entropy losses.

Please choose a person to relate this publication to

Ludwig Schoenholz

S Hüttelmaier

S Leopold

S Steinlechner

S Bachmann

Other publications of authors with the same name

Disambiguation

BibSonomy

Disambiguation of "Schoenholz, Samuel S."

copydeleteadd this publication to your clipboardcommunity posthistory of this postURLDOIBibTeXEndNoteAPAChicagoDIN 1505HarvardMSOffice XML Temperature check: theory and practice for training models with softmax-cross-entropy losses.

Please choose a person to relate this publication to

Ludwig Schoenholz

S Hüttelmaier

S Leopold

S Steinlechner

S Bachmann

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

Temperature check: theory and practice for training models with softmax-cross-entropy losses.