|
Poster
|
Wed 14:30
|
Critical Learning Periods in Deep Networks
Alessandro Achille · Matteo Rovere · Stefano Soatto
|
|
|
Poster
|
Thu 14:30
|
Information Theoretic lower bounds on negative log likelihood
Luis Lastras
|
|
|
Poster
|
Wed 14:30
|
Local SGD Converges Fast and Communicates Little
Sebastian Stich
|
|
|
Poster
|
Thu 14:30
|
Deep learning generalizes because the parameter-function map is biased towards simple functions
Guillermo Valle-Perez · Chico Q. Camargo · Ard Louis
|
|
|
Poster
|
Wed 14:30
|
Gradient Descent Provably Optimizes Over-parameterized Neural Networks
Simon Du · Xiyu Zhai · Barnabás Póczos · Aarti Singh
|
|
|
Poster
|
Wed 14:30
|
Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilience
Vaishnavh Nagarajan · Zico Kolter
|
|
|
Poster
|
Tue 14:30
|
How Powerful are Graph Neural Networks?
Keyulu Xu · Weihua Hu · Jure Leskovec · Stefanie Jegelka
|
|
|
Poster
|
Wed 14:30
|
Subgradient Descent Learns Orthogonal Dictionaries
Yu Bai · Qijia Jiang · Ju Sun
|
|
|
Poster
|
Tue 14:30
|
Excessive Invariance Causes Adversarial Vulnerability
Joern-Henrik Jacobsen · Jens Behrmann · Richard Zemel · Matthias Bethge
|
|
|
Poster
|
Wed 14:30
|
Adaptivity of deep ReLU network for learning in Besov and mixed smooth Besov spaces: optimal rate and curse of dimensionality
Taiji Suzuki
|
|
|
Poster
|
Wed 14:30
|
On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length
Stanislaw Jastrzebski · Zachary Kenton · Nicolas Ballas · Asja Fischer · Yoshua Bengio · Amos Storkey
|
|
|
Oral
|
Tue 8:15
|
A Unified Theory of Early Visual Representations from Retina to Cortex through Anatomically Constrained Deep CNNs
Jack Lindsey · Samuel Ocko · Surya Ganguli · Stephane Deny
|
|
