Mean-field neural networks: learning mappings on Wasserstein space

2022-10-27 · Huyên Pham, Xavier Warin

We study the machine learning task for models with operators mapping between the Wasserstein space of probability measures and a space of functions, like e.g. in mean-field games/control problems. Two classes of neural networks, based on bin density and on cylindrical approximation, are proposed to learn these so-called mean-field functions, and are theoretically supported by universal approximation theorems. We perform several numerical experiments for training these two mean-field neural networks, and show their accuracy and efficiency in the generalization error with various test distributions. Finally, we present different algorithms relying on mean-field neural networks for solving time-dependent mean-field problems, and illustrate our results with numerical tests for the example of a semi-linear partial differential equation in the Wasserstein space of probability measures.

📄 PDF Abstract BibTeX arXiv:2210.15179

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Test 설명 없음

Vector-Valued Distributional Reinforcement Learning Policy Evaluation: A Hilbert Space Embedding Approach

2026-01-26 · Mehrdad Mohammadi, Qi Zheng, Ruoqing Zhu arxiv

We propose an (offline) multi-dimensional distributional reinforcement learning framework (KE-DRL) that leverages Hilbert space mappings to estimate the kernel mean embedding of the multi-dimensional value distribution u…

Reinforcement Learning

Reinforcement Learning with Wasserstein Distance Regularisation, with Applications to Multipolicy Learning

2018-02-12 · Mohammed Amin Abdullah, Aldo Pacchiano, Moez Draief

We describe an application of Wasserstein distance to Reinforcement Learning. The Wasserstein distance in question is between the distribution of mappings of trajectories of a policy into some metric space, and some othe…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

A Riemannian Mean Field Formulation for Two-layer Neural Networks with Batch Normalization

2021-10-17 · Chao Ma, Lexing Ying

The training dynamics of two-layer neural networks with batch normalization (BN) is studied. It is written as the training dynamics of a neural network without BN on a Riemannian manifold. Therefore, we identify BN's eff…

Mean-Field Model for Two-Layer Neural Networks Trained with Consensus-Based Optimization

2025-11-26 · William De Deyn, Michael Herty, Giovanni Samaey arxiv

We study Consensus-Based Optimization (CBO) for two-layer neural network training. We compare the performance of CBO against Adam on two test cases and demonstrate how a hybrid approach, combining CBO with Adam, provides…

Multi-Task Learning

Robust $Q$-learning for mean-field control under Wasserstein uncertainty in common noise

2026-06-18 · Mathieu Laurière, Ariel Neufeld, Kyunghyun Park arxiv

In this article, we present a robust $Q$-learning algorithm for discrete-time mean-field control problems under Wasserstein uncertainty in the common noise law. The algorithm combines a quantization-and-projection scheme…