English
Related papers

Related papers: A Mean-Field Optimal Control Formulation of Deep L…

200 papers

Multi-agent reinforcement learning methods have shown remarkable potential in solving complex multi-agent problems but mostly lack theoretical guarantees. Recently, mean field control and mean field games have been established as a…

Machine Learning · Computer Science 2021-12-20 Kai Cui , Anam Tahir , Mark Sinzger , Heinz Koeppl

We establish a variety of results extending the well-known Pontryagin maximum principle of optimal control to discrete-time optimal control problems posed on smooth manifolds. These results are organized around a new theorem on critical and…

Optimization and Control · Mathematics 2017-07-14 Robert Kipka , Rohit Gupta

We study necessary optimality conditions for the deterministic mean field type free-endpoint optimal control problem. Our study relies on the Lagrangian approach that treats the mean field type control system as a crowd of infinitely many…

Optimization and Control · Mathematics 2025-03-03 Yurii Averboukh , Dmitry Khlopin

In this paper, we introduce a model-based deep-learning approach to solve finite-horizon continuous-time stochastic control problems with jumps. We iteratively train two neural networks: one to represent the optimal policy and the other to…

Machine Learning · Computer Science 2026-01-16 Patrick Cheridito , Jean-Loup Dupret , Donatien Hainaut

We consider a general class of mean field control problems described by stochastic delayed differential equations of McKean-Vlasov type. Two numerical algorithms are provided based on deep learning techniques, one is to directly…

Optimization and Control · Mathematics 2019-10-10 Jean-Pierre Fouque , Zhaoyu Zhang

For an infinite-horizon control problem, the optimal control can be represented by the stable manifold of the characteristic Hamiltonian system of Hamilton-Jacobi-Bellman (HJB) equation in a semiglobal domain. In this paper, we first…

Optimization and Control · Mathematics 2024-05-14 Guoyuan Chen

We propose a mathematical framework to explain implicit regularization from early stopping during the training of overparametrized neural networks. In the mean-field limit, the parameter distribution evolves according to a gradient flow on…

Optimization and Control · Mathematics 2026-03-24 Beatrice Acciaio , Jakob Heiss , Gudmund Pammer , Qinxin Yan

Equilibrium systems are a powerful way to express neural computations. As special cases, they include models of great current interest in both neuroscience and machine learning, such as deep neural networks, equilibrium recurrent neural…

Machine Learning · Computer Science 2022-11-01 Alexander Meulemans , Nicolas Zucchet , Seijin Kobayashi , Johannes von Oswald , João Sacramento

Conditional McKean-Vlasov control problems involve controlling McKean-Vlasov diffusions where the interaction occurs through the law of the state process conditionally on it staying in a domain. Introduced by Lions in his 2016 lectures at…

Probability · Mathematics 2025-10-09 René Carmona , Ludovic Tangpi , Kaiwen Zhang

In this paper we consider a mean field optimal control problem with an aggregation-diffusion constraint, where agents interact through a potential, in the presence of a Gaussian noise term. Our analysis focuses on a PDE system coupling a…

Analysis of PDEs · Mathematics 2019-09-25 Jose A. Carrillo , Edgard A. Pimentel , Vardan K. Voskanyan

We study the problem of optimal portfolio selection under stochastic volatility within a continuous time reinforcement learning framework with portfolio constraints. Exploration is modeled through entropy-regularized relaxed controls, where…

Mathematical Finance · Quantitative Finance 2026-04-27 Thai Nguyen , Pertiny Nkuize

Optimal feedback control with implicit Hamiltonians poses a fundamental challenge for learning-based value function methods due to the absence of closed-form optimal control laws. Recent work~\cite{gelphman2025end} introduced an implicit…

Optimization and Control · Mathematics 2026-04-28 Eric Gelphman , Deepanshu Verma , Nicole Tianjiao Yang , Stanley Osher , Samy Wu Fung

In this paper, we study the optimal control system driven by stochastic differential equations (SDEs) of mean-field type, in which the control variable has two components, the first being absolutely continuous and the second singular. On…

Optimization and Control · Mathematics 2012-11-02 Liangquan Zhang

Given a sequential learning algorithm and a target model, sequential machine teaching aims to find the shortest training sequence to drive the learning algorithm to the target model. We present the first principled way to find such shortest…

Machine Learning · Computer Science 2018-10-17 Laurent Lessard , Xuezhou Zhang , Xiaojin Zhu

We consider an optimal control problem for a system of local continuity equations on a space of probability measures. Such systems can be viewed as macroscopic models of ensembles of non-interacting particles or homotypic individuals,…

Optimization and Control · Mathematics 2021-10-07 Maxim Staritsyn , Nikolay Pogodaev , Roman Chertovskih , Fernando Lobo Pereira

We propose a neural network approach that yields approximate solutions for high-dimensional optimal control problems and demonstrate its effectiveness using examples from multi-agent path finding. Our approach yields controls in a feedback…

Optimization and Control · Mathematics 2022-06-29 Derek Onken , Levon Nurbekyan , Xingjian Li , Samy Wu Fung , Stanley Osher , Lars Ruthotto

Mean field optimal control problems are a class of optimization problems that arise from optimal control when applied to the many body setting. In the noisy case one has a set of controllable stochastic processes and a cost function that is…

Optimization and Control · Mathematics 2021-08-11 Pierfrancesco Urbani

We propose a mean-field optimal control problem for the parameter identification of a given pattern. The cost functional is based on the Wasserstein distance between the probability measures of the modeled and the desired patterns. The…

Optimization and Control · Mathematics 2021-04-08 Martin Burger , Lisa Maria Kreusser , Claudia Totzeck

In this paper we explore the relation between distributionally robust learning and different forms of regularization to enforce robustness of deep neural networks. In particular, starting from a concrete min-max distributionally robust…

Optimization and Control · Mathematics 2022-03-29 Camilo Garcia Trillos , Nicolas Garcia Trillos

Neural network approaches that parameterize value functions have succeeded in approximating high-dimensional optimal feedback controllers when the Hamiltonian admits explicit formulas. However, many practical problems, such as the space…

Optimization and Control · Mathematics 2025-10-08 Eric Gelphman , Deepanshu Verma , Nicole Tianjiao Yang , Stanley Osher , Samy Wu Fung