2000 character limit reached
Diffusion Methods for Generating Transition Paths (2309.10276v1)
Published 19 Sep 2023 in physics.comp-ph, cs.LG, and stat.ML
Abstract: In this work, we seek to simulate rare transitions between metastable states using score-based generative models. An efficient method for generating high-quality transition paths is valuable for the study of molecular systems since data is often difficult to obtain. We develop two novel methods for path generation in this paper: a chain-based approach and a midpoint-based approach. The first biases the original dynamics to facilitate transitions, while the second mirrors splitting techniques and breaks down the original transition into smaller transitions. Numerical results of generated transition paths for the M\"uller potential and for Alanine dipeptide demonstrate the effectiveness of these approaches in both the data-rich and data-scarce regimes.
- Transition path sampling: Throwing ropes over rough mountain passes, in the dark. Annual review of physical chemistry, 53(1):291–318, 2002.
- Linear Convergence Bounds for Diffusion Models via Stochastic Localization. arXiv preprint arXiv:2308.03686, 2023.
- Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions. arXiv preprint arXiv:2209.11215, 2022.
- Adaptive multilevel splitting: Historical perspective and recent results. Chaos: An Interdisciplinary Journal of Nonlinear Science, 29(4), 2019.
- Diffusion models in vision: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023.
- Improved analysis of score-based generative modeling: User-friendly bounds under minimal smoothness assumptions. In International Conference on Machine Learning, pages 4735–4763. PMLR, 2023.
- Martin V Day. Conditional exits for small noise diffusions with characteristic boundary. The Annals of Probability, pages 1385–1419, 1992.
- Valentin De Bortoli. Convergence of denoising diffusion models under the manifold hypothesis. arXiv preprint arXiv:2208.05314, 2022.
- Transition-path theory and path-finding algorithms for the study of rare events. Annual review of physical chemistry, 61:391–420, 2010.
- Computing time scales from reaction coordinates by milestoning. The Journal of chemical physics, 120(23):10880–10889, 2004.
- Wendell H Fleming. Exit probabilities and optimal stochastic control. Applied Mathematics and Optimization, 4:329–346, 1977.
- Estimation of non-normalized statistical models by score matching. Journal of Machine Learning Research, 6(4), 2005.
- Simulating diffusion bridges with score matching. arXiv preprint arXiv:2111.07243, 2021.
- Denoising diffusion probabilistic models. Advances in neural information processing systems, 33:6840–6851, 2020.
- Multiple pathways in conformational transitions of the alanine dipeptide: an application of dynamic importance sampling. Journal of computational chemistry, 27(11):1136–1141, 2006.
- Solving for high-dimensional committor functions using artificial neural networks. Research in the Mathematical Sciences, 6:1–13, 2019.
- Computing committor functions for the study of rare events using deep learning. The Journal of Chemical Physics, 151(5), 2019.
- Convergence of score-based generative modeling for general data distributions. In International Conference on Algorithmic Learning Theory, pages 946–985. PMLR, 2023.
- Reactive trajectories and the transition path process. Probability Theory and Related Fields, 161(1-2):195–244, 2015.
- Generative methods for sampling transition paths in molecular dynamics. ESAIM: Proceedings and Surveys, 73:238–256, 2023.
- F Pinski and A Stuart. Transition paths in molecules: gradient descent in pathspace. J. Chem. Phys, 132:184104, 2010.
- 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.
- Pascal Vincent. A connection between score matching and denoising autoencoders. Neural computation, 23(7):1661–1674, 2011.
- Metadynamics As a Tool for Mapping the Conformational and Free-Energy Space of Peptides: The Alanine Dipeptide Case Study. The Journal of Physical Chemistry B, 114(16):5632–5642, 2010.
- Fast sampling of diffusion models with exponential integrator. arXiv preprint arXiv:2204.13902, 2022.