Manifold-Guided Lyapunov Control with Diffusion Models
Abstract: This paper presents a novel approach to generating stabilizing controllers for a large class of dynamical systems using diffusion models. The core objective is to develop stabilizing control functions by identifying the closest asymptotically stable vector field relative to a predetermined manifold and adjusting the control function based on this finding. To achieve this, we employ a diffusion model trained on pairs consisting of asymptotically stable vector fields and their corresponding Lyapunov functions. Our numerical results demonstrate that this pre-trained model can achieve stabilization over previously unseen systems efficiently and rapidly, showcasing the potential of our approach in fast zero-shot control and generalizability.
- Automated and sound synthesis of lyapunov functions with smt solvers. In Proc. of TACAS, pages 97–114. Springer, 2020.
- Diffusion model based data generation for partial differential equations. ICML workshop on Synergy of Scientific and Machine Learning Modeling, 2023.
- Neural lyapunov control. Advances in neural information processing systems, 32, 2019.
- Diffusion posterior sampling for general noisy inverse problems. In International Conference on Learning Representations, 2023.
- Improving diffusion models for inverse problems using manifold constraints. Advances in Neural Information Processing Systems, 35:25683–25696, 2022.
- Bradley Efron. Tweedie’s formula and selection bias. Journal of the American Statistical Association, 106(496):1602–1614, 2011.
- Manifold preserving guided diffusion. International Conference on Learning Representations, 12, 2024.
- Denoising diffusion probabilistic models. Advances in neural information processing systems, 33:6840–6851, 2020.
- Equivariant diffusion for molecule generation in 3d. In International conference on machine learning, pages 8867–8887. PMLR, 2022.
- Denoising diffusion restoration models. In Advances in Neural Information Processing Systems, 2022.
- Hassan K. Khalil. Nonlinear Systems, Third Edition. Pearson Education, 2002.
- Physics-informed neural network lyapunov functions: Pde characterization, learning, and verification. arXiv preprint arXiv:2312.09131, 2023.
- Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps. Advances in Neural Information Processing Systems, 35:5775–5787, 2022.
- GibbsDDRM: A partially collapsed gibbs sampler for solving blind inverse problems with denoising diffusion restoration. In International Conference on Machine Learning, 2023.
- Ditto: Diffusion-inspired temporal transformer operator. arXiv preprint arXiv:2307.09072, 2023.
- High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 10684–10695, 2022.
- Vikash Sehwag. minimal-diffusion, https://github.com/VSehwag/minimal-diffusion, 2022.
- Denoising diffusion implicit models. International Conference on Learning Representations, 2021.
- Generative modeling by estimating gradients of the data distribution. Advances in neural information processing systems, 32, 2019.
- Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456, 2020.
- Diffusion models: A comprehensive survey of methods and applications. ACM Computing Surveys, 56(4):1–39, 2023.
- Physdiff: Physics-guided human motion diffusion model. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 16010–16021, 2023.
- Neural lyapunov control of unknown nonlinear systems with stability guarantees. Advances in Neural Information Processing Systems, 35:29113–29125, 2022.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.