3 papers
cs.LG2023
Straight-Through meets Sparse Recovery: the Support Exploration Algorithm
Mimoun Mohamed, François Malgouyres, Valentin Emiya +1
The {\it straight-through estimator} (STE) is commonly used to optimize quantized neural networks, yet its contexts of effective performance are still unclear despite empirical suc…
math.OC2017
On the stable recovery of deep structured linear networks under sparsity constraints
Francois Malgouyres
We consider a deep structured linear network under sparsity constraints. We study sharp conditions guaranteeing the stability of the optimal parameters defining the network. More p…
math.OC2006
Estimating the probability law of the codelength as a function of the approximation error in image compression
Francois Malgouyres
After a recollection on compression through a projection onto a polyhedral set (which generalizes the compression by coordinates quantization), we express, in this framework, the p…