4 papers
When low-loss paths make a binary neuron trainable: detecting algorithmic transitions with the connected ensemble
Damien Barbier
We study the connected ensemble, a statistical-mechanics framework that characterizes the formation of low-loss paths in rugged landscapes. First introduced in a previous paper, th…
How to escape atypical regions in the symmetric binary perceptron: a journey through connected-solutions states
Damien Barbier
We study the binary symmetric perceptron model, and in particular its atypical solutions. While the solution-space of this problem is dominated by isolated configurations, it is al…
The phase diagram of compressed sensing with -norm regularization
Damien Barbier, Carlo Lucibello, Luca Saglietti +2
Noiseless compressive sensing is a two-steps setting that allows for undersampling a sparse signal and then reconstructing it without loss of information. The LASSO algorithm, base…
On the Atypical Solutions of the Symmetric Binary Perceptron
Damien Barbier, Ahmed El Alaoui, Florent Krzakala +1
We study the random binary symmetric perceptron problem, focusing on the behavior of rare high-margin solutions. While most solutions are isolated, we demonstrate that these rare s…