Semiconcavity and Sensitivity Analysis in Mean-Field Optimal Control and Applications

Abstract

In this article, we investigate some of the fine properties of the value function associated to an optimal control problem in the Wasserstein space of probability measures. Building on new interpolation and linearisation formulas for non-local flows, we prove semiconcavity estimates for the value function, and establish several variants of the so-called sensitivity relations which provide connections between its superdifferential and the adjoint curves stemming from the maximum principle. We subsequently make use of these results to study the propagation of regularity for the value function along optimal trajectories, as well as to investigate sufficient optimality conditions and optimal feedbacks for mean-field optimal control problems.

arXiv comment55 pages

References in corpus (13)

• The derivation of Swarming models: Mean-Field Limit and Wasserstein distances
• Mean-Field Optimal Control
• Mean-Field Sparse Optimal Control
• A Mean-Field Optimal Control Formulation of Deep Learning
• Instantaneous control of interacting particle systems in the mean-field limit
• The Pontryagin Maximum Principle in the Wasserstein Space
• Differential Inclusions in Wasserstein Spaces: The Cauchy-Lipschitz Framework
• A Pontryagin Maximum Principle in Wasserstein Spaces for Constrained Optimal Control Problems
• Approximate and exact controllability of the continuity equation with a localized vector field
• Generalized Dynamic Programming Principle and Sparse Mean-Field Control Problems
• Minimal time for the continuity equation controlled by a localized perturbation of the velocity vector field
• Mean-Field Neural ODEs via Relaxed Optimal Control
• A Measure Theoretical Approach to the Mean-field Maximum Principle for Training NeurODEs