Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Niru Maheswaranathan

Training Learned Optimizers with Randomly Initialized Learned Optimizers


Jan 14, 2021
Luke Metz, C. Daniel Freeman, Niru Maheswaranathan, Jascha Sohl-Dickstein


  Access Paper or Ask Questions

Reverse engineering learned optimizers reveals known and novel mechanisms


Nov 04, 2020
Niru Maheswaranathan, David Sussillo, Luke Metz, Ruoxi Sun, Jascha Sohl-Dickstein


  Access Paper or Ask Questions

The geometry of integration in text classification RNNs


Oct 28, 2020
Kyle Aitken, Vinay V. Ramasesh, Ankush Garg, Yuan Cao, David Sussillo, Niru Maheswaranathan

* 9+19 pages, 30 figures 

  Access Paper or Ask Questions

Tasks, stability, architecture, and compute: Training more effective learned optimizers, and using them to train themselves


Sep 23, 2020
Luke Metz, Niru Maheswaranathan, C. Daniel Freeman, Ben Poole, Jascha Sohl-Dickstein


  Access Paper or Ask Questions

How recurrent networks implement contextual processing in sentiment analysis


Apr 17, 2020
Niru Maheswaranathan, David Sussillo


  Access Paper or Ask Questions

Using a thousand optimization tasks to learn hyperparameter search strategies


Mar 11, 2020
Luke Metz, Niru Maheswaranathan, Ruoxi Sun, C. Daniel Freeman, Ben Poole, Jascha Sohl-Dickstein


  Access Paper or Ask Questions

From deep learning to mechanistic understanding in neuroscience: the structure of retinal prediction


Dec 12, 2019
Hidenori Tanaka, Aran Nayebi, Niru Maheswaranathan, Lane McIntosh, Stephen A. Baccus, Surya Ganguli

* Neural Information Processing Systems (NeurIPS), 2019 

  Access Paper or Ask Questions

Universality and individuality in neural dynamics across large populations of recurrent networks


Jul 19, 2019
Niru Maheswaranathan, Alex H. Williams, Matthew D. Golub, Surya Ganguli, David Sussillo


  Access Paper or Ask Questions

Reverse engineering recurrent networks for sentiment classification reveals line attractor dynamics


Jun 25, 2019
Niru Maheswaranathan, Alex Williams, Matthew D. Golub, Surya Ganguli, David Sussillo


  Access Paper or Ask Questions

Using learned optimizers to make models robust to input noise


Jun 08, 2019
Luke Metz, Niru Maheswaranathan, Jonathon Shlens, Jascha Sohl-Dickstein, Ekin D. Cubuk


  Access Paper or Ask Questions

Learned optimizers that outperform SGD on wall-clock and test loss


Oct 26, 2018
Luke Metz, Niru Maheswaranathan, Jeremy Nixon, C. Daniel Freeman, Jascha Sohl-Dickstein


  Access Paper or Ask Questions

Guided evolutionary strategies: escaping the curse of dimensionality in random search


Jun 28, 2018
Niru Maheswaranathan, Luke Metz, George Tucker, Jascha Sohl-Dickstein


  Access Paper or Ask Questions

Learning Unsupervised Learning Rules


May 23, 2018
Luke Metz, Niru Maheswaranathan, Brian Cheung, Jascha Sohl-Dickstein


  Access Paper or Ask Questions

Recurrent Segmentation for Variable Computational Budgets


Mar 15, 2018
Lane McIntosh, Niru Maheswaranathan, David Sussillo, Jonathon Shlens


  Access Paper or Ask Questions

Learned Optimizers that Scale and Generalize


Sep 07, 2017
Olga Wichrowska, Niru Maheswaranathan, Matthew W. Hoffman, Sergio Gomez Colmenarejo, Misha Denil, Nando de Freitas, Jascha Sohl-Dickstein

* Final ICML paper after reviewer suggestions 

  Access Paper or Ask Questions

Deep Learning Models of the Retinal Response to Natural Scenes


Feb 06, 2017
Lane T. McIntosh, Niru Maheswaranathan, Aran Nayebi, Surya Ganguli, Stephen A. Baccus

* Advances in Neural Information Processing Systems 29 (2016) 1361-1369 
* L.T.M. and N.M. contributed equally to this work. Presented at NIPS 2016 

  Access Paper or Ask Questions

Deep Unsupervised Learning using Nonequilibrium Thermodynamics


Nov 18, 2015
Jascha Sohl-Dickstein, Eric A. Weiss, Niru Maheswaranathan, Surya Ganguli


  Access Paper or Ask Questions