9 citations · 15 across the 4 of their papers we have counts for
Showing cond-mat.dis-nnShow all
2 papers · 1 filter
cond-mat.dis-nn2026
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…
cond-mat.dis-nn2024★ 5 cited
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…