Author of the publication

The Implicit Bias of Gradient Descent on Separable Data

, , , , and . (2017)cite arxiv:1710.10345Comment: Final JMLR version, with improved discussions over v3. Main improvements in journal version over conference version (v2 appeared in ICLR): We proved the measure zero case for main theorem (with implications for the rates), and the multi-class case.

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.

 

Other publications of authors with the same name

Deep Metric Learning Using Triplet Network, and . Similarity-Based Pattern Recognition, page 84--92. Cham, Springer International Publishing, (2015)Energy awareness in low precision neural networks., , , , and . CoRR, (2022)Norm matters: efficient and accurate normalization schemes in deep networks., , , and . NeurIPS, page 2164-2174. (2018)Task Agnostic Continual Learning Using Online Variational Bayes with Fixed-Point Updates., , , and . CoRR, (2020)Task-Agnostic Continual Learning Using Online Variational Bayes With Fixed-Point Updates., , , and . Neural Comput., 33 (11): 3139-3177 (2021)Neural gradients are lognormally distributed: understanding sparse and quantized training., , , , , and . CoRR, (2020)Semi-supervised deep learning by metric embedding., and . CoRR, (2016)Bayesian Gradient Descent: Online Variational Bayes Learning with Increased Robustness to Catastrophic Forgetting and Weight Pruning, , , and . (2018)cite arxiv:1803.10123.The Implicit Bias of Gradient Descent on Separable Data., , , and . ICLR (Poster), OpenReview.net, (2018)Train longer, generalize better: closing the generalization gap in large batch training of neural networks., , and . NIPS, page 1731-1741. (2017)