3 papers
cs.LG2026
Is Variational Monte Carlo Robust? Sharp Moment Thresholds and Heavy-tailed Stochastic Optimization
Philipp Grohs, Davide Nobile
Variational Monte Carlo (VMC) is a central algorithm in electronic structure theory and has gained renewed importance through modern neural-network ansätze such as FermiNet. At it…
math.OC2026
Robust and Fast Training via Per-Sample Clipping
Davide Nobile, Philipp Grohs
We propose a robust gradient estimator based on per-sample gradient clipping and analyze its properties both theoretically and empirically. We show that the resulting method, per-s…
math.RT2025
Fourier Inversion on the Group of Signatures
Frank Filbir, Davide Nobile, Marco Rauscher
The main objective of this work is to develop a framework for Fourier analysis on the group of signatures, . Employing Kirillov's orbit method, we define the Fou…