Samuel S. Schoenholz
Affiliations:- OpenAI, San Francisco, CA, USA
According to our database1,
Samuel S. Schoenholz
authored at least 38 papers
between 2009 and 2023.
Collaborative distances:
Collaborative distances:
Timeline
Legend:
Book In proceedings Article PhD thesis Dataset OtherLinks
On csauthors.net:
Bibliography
2023
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models.
Trans. Mach. Learn. Res., 2023
Temperature check: theory and practice for training models with softmax-cross-entropy losses.
Trans. Mach. Learn. Res., 2023
Proceedings of the High Performance Computing - 38th International Conference, 2023
2022
Comput. Phys. Commun., 2022
What does a deep neural network confidently perceive? The effective dimension of high certainty class manifolds and their low confidence boundaries.
CoRR, 2022
Proceedings of the International Conference on Machine Learning, 2022
Proceedings of the International Conference on Machine Learning, 2022
2021
Rapid training of deep neural networks without skip connections or normalization layers using Deep Kernel Shaping.
CoRR, 2021
Whitening and Second Order Optimization Both Make Information in the Dataset Unusable During Training, and Can Reduce or Prevent Generalization.
Proceedings of the 38th International Conference on Machine Learning, 2021
Proceedings of the 38th International Conference on Machine Learning, 2021
Proceedings of the 38th International Conference on Machine Learning, 2021
2020
Whitening and second order optimization both destroy information about the dataset, and can make generalization impossible.
CoRR, 2020
CoRR, 2020
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020
Proceedings of the 37th International Conference on Machine Learning, 2020
Proceedings of the 8th International Conference on Learning Representations, 2020
2019
CoRR, 2019
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019
Proceedings of the 7th International Conference on Learning Representations, 2019
2018
Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10, 000-Layer Vanilla Convolutional Neural Networks.
Proceedings of the 35th International Conference on Machine Learning, 2018
Dynamical Isometry and a Mean Field Theory of RNNs: Gating Enables Signal Propagation in Recurrent Neural Networks.
Proceedings of the 35th International Conference on Machine Learning, 2018
Proceedings of the 6th International Conference on Learning Representations, 2018
Proceedings of the 6th International Conference on Learning Representations, 2018
Proceedings of the 6th International Conference on Learning Representations, 2018
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2018
2017
CoRR, 2017
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017
Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practice.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017
Proceedings of the 34th International Conference on Machine Learning, 2017
Proceedings of the 5th International Conference on Learning Representations, 2017
Proceedings of the 5th International Conference on Learning Representations, 2017
2009
Proceedings of the 2009 IEEE International Conference on Robotics and Automation, 2009