activity
20112020
most citedDeep Convolutional Networks on Graph-Structured Data

1.4k citations · 1.6k across the 12 of their papers we have counts for

collaborators

17 papers

cs.LG20202 cited

Provably Efficient Third-Person Imitation from Offline Observation

Aaron Zweig, Joan Bruna

Domain adaptation in imitation learning represents an essential step towards improving generalizability. However, even in the restricted setting of third-person imitation where tra…

cs.LG2019

Stability of Graph Neural Networks to Relative Perturbations

Fernando Gama, Joan Bruna, Alejandro Ribeiro

Graph neural networks (GNNs), consisting of a cascade of layers applying a graph convolution followed by a pointwise nonlinearity, have become a powerful architecture to process si…

cs.LG2019

Pure and Spurious Critical Points: a Geometric Study of Linear Networks

Matthew Trager, Kathlén Kohn, Joan Bruna

The critical locus of the loss function of a neural network is determined by the geometry of the functional space and by the parameterization of this space by the network's weights…

cs.LG201936 cited

Gradient Dynamics of Shallow Univariate ReLU Networks

Francis Williams, Matthew Trager, Claudio Silva +3

We present a theoretical and empirical study of the gradient dynamics of overparameterized shallow ReLU networks with one-dimensional input, solving least-squares interpolation. We…

cs.LG201936 cited

Stability of Graph Scattering Transforms

Fernando Gama, Joan Bruna, Alejandro Ribeiro

Scattering transforms are non-trainable deep convolutional architectures that exploit the multi-scale resolution of a wavelet filter bank to obtain an appropriate representation of…

cs.LG2019

Finding the Needle in the Haystack with Convolutions: on the benefits of architectural bias

Stéphane d'Ascoli, Levent Sagun, Joan Bruna +1

Despite the phenomenal success of deep neural networks in a broad range of learning tasks, there is a lack of theory to understand the way they work. In particular, Convolutional N…