Author of the publication

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.

No persons found for author name Jastrzebski, Stanislaw
add a person with the name Jastrzebski, Stanislaw
 

Other publications of authors with the same name

Width of Minima Reached by Stochastic Gradient Descent is Influenced by Learning Rate to Batch Size Ratio., , , , , , and . ICANN (3), volume 11141 of Lecture Notes in Computer Science, page 392-402. Springer, (2018)Split Batch Normalization: Improving Semi-Supervised Learning under Domain Shift., , and . CoRR, (2019)Non-linear ICA based on Cramer-Wold metric., , , , and . CoRR, (2019)Deep Nets Don't Learn via Memorization., , , , , , , , and . ICLR (Workshop), OpenReview.net, (2017)Parameter-Efficient Transfer Learning for NLP., , , , , , , and . ICML, volume 97 of Proceedings of Machine Learning Research, page 2790-2799. PMLR, (2019)Dynamical Isometry is Achieved in Residual Networks in a Universal Way for any Activation Function., , , , and . AISTATS, volume 89 of Proceedings of Machine Learning Research, page 2221-2230. PMLR, (2019)Three Factors Influencing Minima in SGD., , , , , , and . CoRR, (2017)DNN's Sharpest Directions Along the SGD Trajectory., , , , , and . CoRR, (2018)Residual Connections Encourage Iterative Inference., , , , , and . ICLR (Poster), OpenReview.net, (2018)On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length., , , , , and . ICLR (Poster), OpenReview.net, (2019)