3 papers
cs.LG2021
Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances
Berfin Şimşek, François Ged, Arthur Jacot +4
We study how permutation symmetries in overparameterized multi-layer neural networks generate `symmetry-induced' critical points. Assuming a network with layers of minimal wi…
math.PR2020
Moran model with simultaneous strong and weak selections: convergence towards a -Wright-Fisher SDE
François Gaston Ged
We study a population model of fixed size undergoing strong selection where individuals accumulate beneficial mutations, namely the Moran model with selection. In a specific settin…
math.PR2019
Intrinsic area near the origin for self-similar growth-fragmentations and related random surfaces
François Gaston Ged
We study the behaviour of a natural measure defined on the leaves of the genealogical tree of some branching processes, namely self-similar growth-fragmentation processes. Each par…