Sign in
Madhu Advani
Publication Activity (10 Years)
Years Active: 2016-2020
Publications (10 Years): 6
Top Topics
Lossy Compression
Bayes Optimal
Training Speed
Neural Network
Top Venues
CoRR
NIPS
ICLR (Poster)
NeurIPS
</>
Publications
</>
Julia Steinberg
,
Madhu Advani
,
Haim Sompolinsky
A new role for circuit expansion for learning in neural networks.
CoRR
(2020)
Sebastian Goldt
,
Madhu Advani
,
Andrew M. Saxe
,
Florent Krzakala
,
Lenka Zdeborová
Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup.
NeurIPS
(2019)
Stefano Recanatesi
,
Matthew Farrell
,
Madhu Advani
,
Timothy Moore
,
Guillaume Lajoie
,
Eric Shea-Brown
Dimensionality compression and expansion in Deep Neural Networks.
CoRR
(2019)
Andrew M. Saxe
,
Yamini Bansal
,
Joel Dapello
,
Madhu Advani
,
Artemy Kolchinsky
,
Brendan D. Tracey
,
David D. Cox
On the Information Bottleneck Theory of Deep Learning.
ICLR (Poster)
(2018)
Yamini Bansal
,
Madhu Advani
,
David D. Cox
,
Andrew M. Saxe
Minnorm training: an algorithm for training over-parameterized deep neural networks.
CoRR
(2018)
Madhu Advani
,
Surya Ganguli
An equivalence between high dimensional Bayes optimal inference and M-estimation.
NIPS
(2016)