The main difficulty that arises in the analysis of most machine learning...
We consider a commonly studied supervised classification of a synthetic
...
We introduce tramp, standing for TRee Approximate Message Passing, a pyt...
Statistical learning theory provides bounds of the generalization gap, u...
We consider the problem of compressed sensing and of (real-valued) phase...
Using a low-dimensional parametrization of signals is a generic and powe...
Heuristic tools from statistical physics have been used in the past to l...