SOURCE-LINKED INTELLIGENCE

A Function-Space Approach to the Statistical Mechanics of Learning Dynamics

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

Deep neural networks exhibit regular macroscopic behavior despite highly nonlinear dynamics in vast parameter spaces. We develop a statistical-mechanical description of learning directly in function space, treating parameter configurations as microscopic realizations and functions with their dynamical operators as macroscopic variables. For mean-squared loss, the exact error dynamics are governed by the learning operator \(M=JJ^\ast\). Combining the dynamical Boltzmann weight of the conditional stochastic dynamics with the parameter-space density of states, whose local curvature defines a stat

Read original source ↗ Open in workspace

recordType

paper

region

Global