( en | de | ru )

 

Disambiguation of "Sohl-Dickstein, Jascha"

Author of the publication

copydeleteadd this publication to your clipboard
Understanding and correcting pathologies in the training of learned optimizers.

, , , , and . ICML, volume 97 of Proceedings of Machine Learning Research, page 4556-4565. PMLR, (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

Understanding and correcting pathologies in the training of learned optimizers., , , , and . ICML, volume 97 of Proceedings of Machine Learning Research, page 4556-4565. PMLR, (2019)The large learning rate phase of deep learning: the catapult mechanism, , , , and . arXiv preprint arXiv:2003.02218, (2020)Measuring the Effects of Data Parallelism on Neural Network Training., , , , , and . J. Mach. Learn. Res., (2019)Exact posterior distributions of wide Bayesian neural networks., , , , and . CoRR, (2020)Whitening and second order optimization both destroy information about the dataset, and can make generalization impossible., , , , and . CoRR, (2020)A new method for parameter estimation in probabilistic models: Minimum probability flow., , and . CoRR, (2020)Neural reparameterization improves structural optimization., , and . CoRR, (2019)VeLO: Training Versatile Learned Optimizers by Scaling Up., , , , , , , , , and 1 other author(s). CoRR, (2022)Towards NNGP-guided Neural Architecture Search., , , , and . CoRR, (2020)Unrolled Generative Adversarial Networks., , , and . ICLR (Poster), OpenReview.net, (2017)