( en | de | ru )

 

Disambiguation of "Schoenholz, Samuel S."

Author of the publication

copydeleteadd this publication to your clipboard
Learn2Hop: Learned Optimization on Rough Landscapes.

, , , and . ICML, volume 139 of Proceedings of Machine Learning Research, page 7643-7653. PMLR, (2021)

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 Danischewski

S Steinlechner

S Hüttelmaier

S Leopold

 

Other publications of authors with the same name

On the infinite width limit of neural networks with a standard parameterization., , , and . CoRR, (2020)Explaining the Learning Dynamics of Direct Feedback Alignment., , , , and . ICLR (Workshop), OpenReview.net, (2017)Fast Finite Width Neural Tangent Kernel., , and . ICML, volume 162 of Proceedings of Machine Learning Research, page 17018-17044. PMLR, (2022)Specialization as an optimal strategy under varying external conditions., , , , and . ICRA, page 1941-1946. IEEE, (2009)Dynamical Isometry and a Mean Field Theory of LSTMs and GRUs., , , , , , and . CoRR, (2019)Rapid training of deep neural networks without skip connections or normalization layers using Deep Kernel Shaping., , , , , , and . CoRR, (2021)Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models, , , , , , , , , and 441 other author(s). (2022)cite arxiv:2206.04615Comment: 27 pages, 17 figures + references and appendices, repo: https://github.com/google/BIG-bench.Dynamical Isometry and a Mean Field Theory of RNNs: Gating Enables Signal Propagation in Recurrent Neural Networks., , and . ICML, volume 80 of Proceedings of Machine Learning Research, page 872-881. PMLR, (2018)Gradients are Not All You Need., , , and . CoRR, (2021)Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent., , , , , and . CoRR, (2019)