Incremental Learning in Mirror Flows
Raphaël Berthier, Loucas Pillaud-Vivien
math.OC cs.LG stat.ML
Abstract
We study mirror flows generated by a convex quadratic loss and a general convex lower semicontinuous mirror potential. We show that, when initialized near the boundary of the domain of the mirror potential, their rescaled trajectories converge to a limiting mirror flow whose potential is the indicator function of the domain. In this limit, the primal variable minimizes the loss over a time-dependent hypothesis set: the subdifferential of the support function of the domain, evaluated at the dual variable. This characterization provides a general mechanism for incremental learning in mirror flows.
Topics
Classified with taxonomy v2 on Wed, 2 Sept 2026.