Author of the publication

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.

No persons found for author name Maheswaranathan, Niru
add a person with the name Maheswaranathan, Niru
 

Other publications of authors with the same name

The geometry of integration in text classification RNNs., , , , , and . CoRR, (2020)Reverse engineering learned optimizers reveals known and novel mechanisms., , , , and . NeurIPS, page 19910-19922. (2021)Understanding How Encoder-Decoder Architectures Attend., , , and . NeurIPS, page 22184-22195. (2021)Using learned optimizers to make models robust to input noise., , , , and . CoRR, (2019)Learning to Learn Without Labels., , , and . ICLR (Workshop), OpenReview.net, (2018)Reverse engineering recurrent networks for sentiment classification reveals line attractor dynamics., , , , and . NeurIPS, page 15670-15679. (2019)Tasks, stability, architecture, and compute: Training more effective learned optimizers, and using them to train themselves., , , , and . CoRR, (2020)Recurrent Segmentation for Variable Computational Budgets., , , and . CoRR, (2017)Meta-Learning Update Rules for Unsupervised Representation Learning., , , and . ICLR, OpenReview.net, (2019)Recurrent Segmentation for Variable Computational Budgets., , , and . CVPR Workshops, page 1648-1657. Computer Vision Foundation / IEEE Computer Society, (2018)