4.6k citations · 13.8k across the 80 of their papers we have counts for
4 papers · 1 filter
FeTa: A DCA Pruning Algorithm with Generalization Error Guarantees
Konstantinos Pitas, Mike Davies, Pierre Vandergheynst
Recent DNN pruning algorithms have succeeded in reducing the number of parameters in fully connected layers, often with little or no drop in classification accuracy. However, most…
Spectrally approximating large graphs with smaller graphs
Andreas Loukas, Pierre Vandergheynst
How does coarsening affect the spectrum of a general graph? We provide conditions such that the principal eigenvalues and eigenspaces of a coarsened and original graph Laplacian ma…
Joint Estimation of Room Geometry and Modes with Compressed Sensing
Helena Peić Tukuljac, Thach Pham Vu, Hervé Lissek +1
Acoustical behavior of a room for a given position of microphone and sound source is usually described using the room impulse response. If we rely on the standard uniform sampling,…
PAC-Bayesian Margin Bounds for Convolutional Neural Networks
Konstantinos Pitas, Mike Davies, Pierre Vandergheynst
Recently the generalization error of deep neural networks has been analyzed through the PAC-Bayesian framework, for the case of fully connected layers. We adapt this approach to th…