Showing 2026Show all
2 papers · 1 filter
cond-mat.dis-nn2026
Sampling at intermediate temperatures is optimal for training large language models in protein structure prediction
L. Ghiringhelli, A. Zambon, G. Tiana
Using a statistical mechanics framework, we investigate the parameter space of transformer models trained on protein sequence data. We sample the loss landscape at varying temperat…
cond-mat.dis-nn2026
Controlled Langevin Dynamics for Sampling of Feedforward Neural Networks Trained with Minibatches
Alessandro Zambon, Francesca Caruso, Riccardo Zecchina +1
Sampling the parameter space of artificial neural networks according to a Boltzmann distribution provides insight into the geometry of low-loss solutions and offers an alternative…