Neural Mean-Field Games: Extending Mean-Field Game Theory with Neural Stochastic Differential Equations

• URL: http://arxiv.org/abs/2504.13228v3
• Date: Fri, 17 Oct 2025 07:40:38 GMT
• Title: Neural Mean-Field Games: Extending Mean-Field Game Theory with Neural Stochastic Differential Equations
• Authors: Anna C. M. Thöni, Yoram Bachrach, Tal Kachman,
• Abstract summary: Mean-field game theory relies on approximating games that are intractible to model due to a large to infinite population of players.<n>We introduce neural mean-field games: a combination of mean-field theory and deep learning in the form of neural differential equations.<n>The model is data-driven, lightweight, and can learn extensive strategic interactions that are hard to capture using mean-field theory alone.
• Score: 4.765409175050468
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Mean-field game theory relies on approximating games that are intractible to model due to a very large to infinite population of players. While these kinds of games can be solved analytically via the associated system of partial derivatives, this approach is not model-free, can lead to the loss of the existence or uniqueness of solutions, and may suffer from modelling bias. To reduce the dependency between the model and the game, we introduce neural mean-field games: a combination of mean-field game theory and deep learning in the form of neural stochastic differential equations. The resulting model is data-driven, lightweight, and can learn extensive strategic interactions that are hard to capture using mean-field theory alone. In addition, the model is based on automatic differentiation, making it more robust and objective than approaches based on finite differences. We highlight the efficiency and flexibility of our approach by solving two mean-field games that vary in their complexity, observability, and the presence of noise. Lastly, we illustrate the model's robustness by simulating viral dynamics based on real-world data. Here, we demonstrate that the model's ability to learn from real-world data helps to accurately model the evolution of an epidemic outbreak. Using these results, we show that the model is flexible, generalizable, and requires few observations to learn the distribution underlying the data.

Related papers

• Game-theoretic distributed learning of generative models for heterogeneous data collections [2.1485350418225244]
  Local models can be treated as black boxes'' with the ability to learn their parameters from data.<n>We formulate the learning of the local models as a cooperative game starting from the principles of game theory.
  arXiv  Detail & Related papers  (2025-11-03T16:52:04Z)
• On Defining Neural Averaging [0.552480439325792]
  Amortized Model Ensembling (AME) is a data-free meta-optimization approach that treats model differences as pseudogradients to guide neural weight updates.<n>We show AME produces averaged neural solutions that outperform both individual experts and model soup baselines.
  arXiv  Detail & Related papers  (2025-08-20T16:28:08Z)
• A Complete Decomposition of KL Error using Refined Information and Mode Interaction Selection [11.994525728378603]
  We revisit the classical formulation of the log-linear model with a focus on higher-order mode interactions. We find that our learned distributions are able to more efficiently use the finite amount of data which is available in practice.
  arXiv  Detail & Related papers  (2024-10-15T18:08:32Z)
• Learning Divergence Fields for Shift-Robust Graph Representations [73.11818515795761]
  In this work, we propose a geometric diffusion model with learnable divergence fields for the challenging problem with interdependent data. We derive a new learning objective through causal inference, which can guide the model to learn generalizable patterns of interdependence that are insensitive across domains.
  arXiv  Detail & Related papers  (2024-06-07T14:29:21Z)
• Likelihood Based Inference in Fully and Partially Observed Exponential Family Graphical Models with Intractable Normalizing Constants [4.532043501030714]
  Probabilistic graphical models that encode an underlying Markov random field are fundamental building blocks of generative modeling.<n>This paper is to demonstrate that full likelihood based analysis of these models is feasible in a computationally efficient manner.
  arXiv  Detail & Related papers  (2024-04-27T02:58:22Z)
• Towards Theoretical Understandings of Self-Consuming Generative Models [56.84592466204185]
  This paper tackles the emerging challenge of training generative models within a self-consuming loop. We construct a theoretical framework to rigorously evaluate how this training procedure impacts the data distributions learned by future models. We present results for kernel density estimation, delivering nuanced insights such as the impact of mixed data training on error propagation.
  arXiv  Detail & Related papers  (2024-02-19T02:08:09Z)
• Evaluation of Differentially Constrained Motion Models for Graph-Based Trajectory Prediction [1.1947990549568765]
  This research investigates the performance of various motion models in combination with numerical solvers for the prediction task. The study shows that simpler models, such as low-order integrator models, are preferred over more complex, e.g., kinematic models, to achieve accurate predictions.
  arXiv  Detail & Related papers  (2023-04-11T10:15:20Z)
• Dataless Knowledge Fusion by Merging Weights of Language Models [51.8162883997512]
  Fine-tuning pre-trained language models has become the prevalent paradigm for building downstream NLP models. This creates a barrier to fusing knowledge across individual models to yield a better single model. We propose a dataless knowledge fusion method that merges models in their parameter space.
  arXiv  Detail & Related papers  (2022-12-19T20:46:43Z)
• Dynamic Latent Separation for Deep Learning [67.62190501599176]
  A core problem in machine learning is to learn expressive latent variables for model prediction on complex data. Here, we develop an approach that improves expressiveness, provides partial interpretation, and is not restricted to specific applications.
  arXiv  Detail & Related papers  (2022-10-07T17:56:53Z)
• Learning from aggregated data with a maximum entropy model [73.63512438583375]
  We show how a new model, similar to a logistic regression, may be learned from aggregated data only by approximating the unobserved feature distribution with a maximum entropy hypothesis. We present empirical evidence on several public datasets that the model learned this way can achieve performances comparable to those of a logistic model trained with the full unaggregated data.
  arXiv  Detail & Related papers  (2022-10-05T09:17:27Z)
• Diffusion models as plug-and-play priors [98.16404662526101]
  We consider the problem of inferring high-dimensional data $mathbfx$ in a model that consists of a prior $p(mathbfx)$ and an auxiliary constraint $c(mathbfx,mathbfy)$. The structure of diffusion models allows us to perform approximate inference by iterating differentiation through the fixed denoising network enriched with different amounts of noise.
  arXiv  Detail & Related papers  (2022-06-17T21:11:36Z)
• Discrepancy Modeling Framework: Learning missing physics, modeling systematic residuals, and disambiguating between deterministic and random effects [4.459306403129608]
  In modern dynamical systems, discrepancies between model and measurement can lead to poor quantification. We introduce a discrepancy modeling framework to identify the missing physics and resolve the model-measurement mismatch.
  arXiv  Detail & Related papers  (2022-03-10T05:37:24Z)
• X-model: Improving Data Efficiency in Deep Learning with A Minimax Model [78.55482897452417]
  We aim at improving data efficiency for both classification and regression setups in deep learning. To take the power of both worlds, we propose a novel X-model. X-model plays a minimax game between the feature extractor and task-specific heads.
  arXiv  Detail & Related papers  (2021-10-09T13:56:48Z)
• Approximate Latent Force Model Inference [1.3927943269211591]
  latent force models offer an interpretable alternative to purely data driven tools for inference in dynamical systems. We show that a neural operator approach can scale our model to thousands of instances, enabling fast, distributed computation.
  arXiv  Detail & Related papers  (2021-09-24T09:55:00Z)
• Model-agnostic multi-objective approach for the evolutionary discovery of mathematical models [55.41644538483948]
  In modern data science, it is more interesting to understand the properties of the model, which parts could be replaced to obtain better results. We use multi-objective evolutionary optimization for composite data-driven model learning to obtain the algorithm's desired properties.
  arXiv  Detail & Related papers  (2021-07-07T11:17:09Z)
• A Probabilistic State Space Model for Joint Inference from Differential Equations and Data [23.449725313605835]
  We show a new class of solvers for ordinary differential equations (ODEs) that phrase the solution process directly in terms of Bayesian filtering. It then becomes possible to perform approximate Bayesian inference on the latent force as well as the ODE solution in a single, linear complexity pass of an extended Kalman filter. We demonstrate the expressiveness and performance of the algorithm by training a non-parametric SIRD model on data from the COVID-19 outbreak.
  arXiv  Detail & Related papers  (2021-03-18T10:36:09Z)
• Contextual Dropout: An Efficient Sample-Dependent Dropout Module [60.63525456640462]
  Dropout has been demonstrated as a simple and effective module to regularize the training process of deep neural networks. We propose contextual dropout with an efficient structural design as a simple and scalable sample-dependent dropout module. Our experimental results show that the proposed method outperforms baseline methods in terms of both accuracy and quality of uncertainty estimation.
  arXiv  Detail & Related papers  (2021-03-06T19:30:32Z)
• Sufficiently Accurate Model Learning for Planning [119.80502738709937]
  This paper introduces the constrained Sufficiently Accurate model learning approach. It provides examples of such problems, and presents a theorem on how close some approximate solutions can be. The approximate solution quality will depend on the function parameterization, loss and constraint function smoothness, and the number of samples in model learning.
  arXiv  Detail & Related papers  (2021-02-11T16:27:31Z)
• Firearm Detection via Convolutional Neural Networks: Comparing a Semantic Segmentation Model Against End-to-End Solutions [68.8204255655161]
  Threat detection of weapons and aggressive behavior from live video can be used for rapid detection and prevention of potentially deadly incidents. One way for achieving this is through the use of artificial intelligence and, in particular, machine learning for image analysis. We compare a traditional monolithic end-to-end deep learning model and a previously proposed model based on an ensemble of simpler neural networks detecting fire-weapons via semantic segmentation.
  arXiv  Detail & Related papers  (2020-12-17T15:19:29Z)
• Learning physically consistent mathematical models from data using group sparsity [2.580765958706854]
  In areas like biology, high noise levels, sensor-induced correlations, and strong inter-system variability can render data-driven models nonsensical or physically inconsistent. We show several applications from systems biology that demonstrate the benefits of enforcing $textitpriors$ in data-driven modeling.
  arXiv  Detail & Related papers  (2020-12-11T14:45:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.