The asymptotic behavior of stochastic gradient algorithms is studied. Relying on some results of differential geometry (Lojasiewicz gradient inequality), the almost sure pointconve...
Set-based analysis is a constraint-based whole program analysis that is applicable to functional and objectoriented programming languages. Unfortunately, the analysis is useless f...
— We consider whether the off-line compilation of a set of Service Level Agreements (SLAs) into low-level management policies can lead to the runtime maximization of the overall ...
Modeling long-term dependencies in time series has proved very difficult to achieve with traditional machine learning methods. This problem occurs when considering music data. In ...
We propose a sinogram restoration method which consists of a patch-wise non-linear processing, based on a sparsity prior in terms of a learned dictionary. An off-line learning pro...