10 citations · 10 across the 6 of their papers we have counts for
Showing 2026 · cs.LGShow all
2 papers · 2 filters
cs.LG2026
Learning features from Newton's algorithm: a way to accelerate nonlinear parametrized PDE solvers
Rémy Vallot, Florian de Vuyst, Thibault Dairay +1
It is well known that Newton's method converges faster when the initial guess is closer to a root of a system of nonlinear equations. In this paper, a two-stage Newton initial gues…
cs.LG2026
Correcting Source Mismatch in Flow Matching with Radial-Angular Transport
Fouad Oubari, Mathilde Mougeot
Flow Matching is typically built from Gaussian sources and Euclidean probability paths. For heavy-tailed or anisotropic data, however, a Gaussian source induces a structural mismat…