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 Madhu Advani

A new role for circuit expansion for learning in neural networks


Aug 19, 2020
Julia Steinberg, Madhu Advani, Haim Sompolinsky

* 12+10 pages, 13 figures 

  Access Paper or Ask Questions

Dimensionality compression and expansion in Deep Neural Networks


Jun 02, 2019
Stefano Recanatesi, Matthew Farrell, Madhu Advani, Timothy Moore, Guillaume Lajoie, Eric Shea-Brown

* Submitted to NeurIPS 2019. First two authors contributed equally 

  Access Paper or Ask Questions

Minnorm training: an algorithm for training over-parameterized deep neural networks


Jun 21, 2018
Yamini Bansal, Madhu Advani, David D Cox, Andrew M Saxe


  Access Paper or Ask Questions

An equivalence between high dimensional Bayes optimal inference and M-estimation


Sep 22, 2016
Madhu Advani, Surya Ganguli

* To appear in NIPS 2016 

  Access Paper or Ask Questions

Statistical Mechanics of High-Dimensional Inference


Feb 22, 2016
Madhu Advani, Surya Ganguli

* Phys. Rev. X 6, 031034 (2016) 
* See http://ganguli-gang.stanford.edu/pdf/HighDimInf.Supp.pdf for supplementary material 

  Access Paper or Ask Questions

Statistical mechanics of complex neural systems and high dimensional data


Jan 30, 2013
Madhu Advani, Subhaneil Lahiri, Surya Ganguli

* 72 pages, 8 figures, iopart.cls, to appear in JSTAT 

  Access Paper or Ask Questions