14 citations · 17 across the 5 of their papers we have counts for
5 papers
Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study
Franck Gabriel, François Ged, Maria Han Veiga +1
Diffusion models now set the benchmark in high-fidelity generative sampling, yet they can, in principle, be prone to memorization. In this case, their learned score overfits the fi…
Saddle-to-Saddle Dynamics in Deep Linear Networks: Small Initialization Training, Symmetry, and Sparsity
Arthur Jacot, François Ged, Berfin Şimşek +2
The dynamics of Deep Linear Networks (DLNs) is dramatically affected by the variance of the parameters at initialization . For DLNs of width , we show a phase transit…
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…
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…
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…