AI RESEARCH

Asymptotic and Finite-Time Guarantees for Langevin-Based Temperature Annealing in InfoNCE

arXiv CS.LG

ArXi:2603.12552v1 Announce Type: new The InfoNCE loss in contrastive learning depends critically on a temperature parameter, yet its dynamics under fixed versus annealed schedules remain poorly understood. We provide a theoretical analysis by modeling embedding evolution under Langevin dynamics on a compact Riemannian manifold.