2 papers
cs.LG2026
Global Optimization via Softmin Energy Minimization
Andrea Agazzi, Vittorio Carlei, Marco Romito +1
Global optimization, particularly for non-convex functions with multiple local minima, poses significant challenges for traditional gradient-based methods. While metaheuristic appr…
math.PR2026
Stochastic Scaling Limits and Synchronization by Noise in Deep Transformer Models
Andrea Agazzi, Giuseppe Bruno, Eloy Mosig GarcÃa +2
We prove pathwise convergence of the layerwise evolution of tokens in a finite-depth, finite-width transformer model with MultiLayer Perceptron (MLP) blocks to a continuous-time st…