5 papers
Multiresolution Adaptive Block-Coordinate Forward-Backward for Image Reconstruction
Edgar Desainte-Maréville, Marion Foare, Paulo Gonçalves +2
Classical first-order optimization methods for imaging inverse problems scale poorly with image resolution. Wavelet based multilevel strategies can accelerate convergence under str…
A flexible block-coordinate forward-backward algorithm for non-smooth and non-convex optimization
Luis Briceño-Arias, Paulo Gonçalves, Guillaume Lauga +2
Block coordinate descent (BCD) methods are prevalent in large scale optimization problems due to the low memory and computational costs per iteration, the predisposition to paralle…
A Rescaling-Invariant Lipschitz Bound Based on Path-Metrics for Modern ReLU Network Parameterizations
Antoine Gonon, Nicolas Brisebarre, Elisa Riccietti +1
Robustness with respect to weight perturbations underpins guarantees for generalization, pruning and quantization. Existing guarantees rely on Lipschitz bounds in parameter space,…
Butterfly factorization with error guarantees
Quoc-Tung Le, Léon Zheng, Elisa Riccietti +1
In this paper, we investigate the butterfly factorization problem, i.e., the problem of approximating a matrix by a product of sparse and structured factors. We propose a new forma…
A path-norm toolkit for modern networks: consequences, promises and challenges
Antoine Gonon, Nicolas Brisebarre, Elisa Riccietti +1
This work introduces the first toolkit around path-norms that fully encompasses general DAG ReLU networks with biases, skip connections and any operation based on the extraction of…