Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
153 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Response Theory via Generative Score Modeling (2402.01029v3)

Published 1 Feb 2024 in physics.data-an and cs.LG

Abstract: We introduce an approach for analyzing the responses of dynamical systems to external perturbations that combines score-based generative modeling with the Generalized Fluctuation-Dissipation Theorem (GFDT). The methodology enables accurate estimation of system responses, including those with non-Gaussian statistics. We numerically validate our approach using time-series data from three different stochastic partial differential equations of increasing complexity: an Ornstein-Uhlenbeck process with spatially correlated noise, a modified stochastic Allen-Cahn equation, and the 2D Navier-Stokes equations. We demonstrate the improved accuracy of the methodology over conventional methods and discuss its potential as a versatile tool for predicting the statistical behavior of complex dynamical systems.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (57)
  1. High-dimensional inference: a statistical mechanics perspective. arXiv preprint arXiv:2010.14863, 2020.
  2. Efficient state and parameter estimation for high-dimensional nonlinear system identification with application to meg brain network modeling. arXiv preprint arXiv:2104.02827, 2021.
  3. Deep neural networks are effective at learning high-dimensional hilbert-valued functions from limited data. arXiv preprint arXiv:2012.06081, 2020.
  4. Ground state structures in ordered binary alloys with second neighbor interactions. Acta Metallurgica, 20(3):423–433, 1972.
  5. Anderson, B. D. Reverse-time diffusion equation models. Stochastic Processes and their Applications, 12(3):313–326, 1982.
  6. Causal analysis, correlation-response, and dynamic cavity. In Journal of Physics: Conference Series, volume 699, pp.  012002. IOP Publishing, 2016.
  7. Authors. Deep learning of causal structures in high dimensions under data limitations. Nature Machine Intelligence, Number(Number):Pages, Yeara.
  8. Authors. Large-scale nonlinear granger causality for inferring directed dependence from short multivariate time-series data. Scientific Reports, Number(Number):Pages, Yearb.
  9. Badwan, N. Perspective Chapter: International Financial Markets and Financial Capital Flows - Forms, Factors and Assessment Tools. IntechOpen, 2022. doi: 10.5772/intechopen.102572. URL https://www.intechopen.com/chapters/80683.
  10. Understanding causation via correlations and linear response theory. Physical Review Research, 2(4):043436, 2020.
  11. Emergence of scaling in random networks. Science, 286:509–512, 1999.
  12. Deep neural network approximation theory for high-dimensional functions. arXiv preprint arXiv:2112.14523, 2021.
  13. Unpaired downscaling of fluid flows with diffusion bridges. arXiv preprint arXiv:2305.01822, 2023.
  14. Boyd, J. P. Chebyshev and Fourier Spectral Methods. Dover Books on Mathematics. Dover Publications, Mineola, NY, second edition, 2001. ISBN 0486411834 9780486411835.
  15. Causality analysis: Identifying the leading element in a coupled dynamical system. PLOS ONE, 10(6):e0131226, 2015.
  16. Quantifying uncertainty for predictions with model error in non-gaussian systems with intermittency. Nonlinearity, 25(9):2543, 2012.
  17. Machine learning for fluid mechanics. Annual Review of Fluid Mechanics, 52:477–508, 2019.
  18. Pattern formation in three-dimensional reaction–diffusion systems. Physica D: Nonlinear Phenomena, 132(3):339–362, 1999.
  19. Discovering causal relations and equations from data. arXiv preprint arXiv:2305.13341, 2023.
  20. Some recent progress in singular stochastic partial differential equations. Bulletin of the American Mathematical Sociefty, 57(3):409–454, 2020.
  21. Daum, F. Nonlinear filters: beyond the kalman filter. IEEE Aerospace and Electronic Systems Magazine, 20(8):57–69, 2005.
  22. Critical phenomena in complex networks. Reviews of Modern Physics, 80:1275, 2008.
  23. A data-driven framework for dimensionality reduction and causal inference in climate fields. 2023. doi: 10.48550/arXiv.2306.14433. URL https://arxiv.org/abs/2306.14433.
  24. Approaching complexity by stochastic methods: From biological systems to turbulence. Physics Reports, 506(5):87–162, 2011.
  25. The physics of climate variability and climate change. Reviews of Modern Physics, 92(3):035002, 2020.
  26. Granger, C. W. Investigating causal relations by econometric models and cross-spectral methods. Econometrica: journal of the Econometric Society, pp.  424–438, 1969.
  27. Climate response using a three-dimensional operator based on the fluctuation–dissipation theorem. Journal of the atmospheric sciences, 64(7):2558–2575, 2007.
  28. Multiplex pagerank. PLoS ONE, 8:e78293, 2013.
  29. Denoising diffusion probabilistic models. Advances in neural information processing systems, 33:6840–6851, 2020.
  30. Network modeling of dynamic brain interactions predicts emergence of neural information that supports human cognitive behavior. PLOS Biology, 2021. doi: 10.1371/journal.pbio.3001686. URL https://journals.plos.org/plosbiology/article?id=10.1371/journal.pbio.3001686.
  31. Jumper, J. et al. Highly accurate protein structure prediction with alphafold. Nature, 596:583–589, 2021.
  32. Causal machine learning: A survey and open problems. arXiv preprint arXiv:2206.15475, 2022.
  33. Stochastic paleoclimatology: Modeling the epica ice core climate records. Chaos: An Interdisciplinary Journal of Nonlinear Science, 33(9):093132, 2023.
  34. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
  35. A study of the diffusion equation with increase in the amount of substance, and its application to a biological problem. übersetzung aus: Bulletin of the moscow state university series a 1: 1-26, 1937. Selected Works of AN Kolmogorov, 1.
  36. Reaction-diffusion model as a framework for understanding biological pattern formation. science, 329(5999):1616–1620, 2010.
  37. Neural tuning and representational geometry. Nature Reviews Neuroscience, 22(11):703–718, 2021.
  38. Short-tailed temperature distributions over north america and implications for future changes in extremes. Geophysical Research Letters, 42(20):8577–8585, 2015.
  39. Lucarini, V. Revising and extending the linear response theory for statistical mechanical systems: Evaluating observables as predictors and predictands. Journal of Statistical Physics, 173(6):1698–1721, 2018.
  40. Fluctuation–dissipation: response theory in statistical physics. Physics reports, 461(4-6):111–195, 2008.
  41. The influence of the quasi-biennial oscillation on the madden–julian oscillation. Nature Reviews Earth & Environment, 2(7):477–489, 2021.
  42. Community structure in time-dependent, multiscale, and multiplex networks. Science, 328:876–878, 2010.
  43. Pearl, J. Causal inference in statistics: An overview. 2009.
  44. Identification and interpretation of nonnormality in atmospheric time series. Geophysical Research Letters, 43(10):5425–5434, 2016.
  45. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18, pp.  234–241. Springer, 2015.
  46. Schreiber, T. Measuring information transfer. Physical review letters, 85(2):461, 2000.
  47. Fokker–planck approximation of the master equation in molecular biology. Computing and Visualization in Science, 12:37–50, 2009.
  48. Deep unsupervised learning using nonequilibrium thermodynamics. In International conference on machine learning, pp.  2256–2265. PMLR, 2015.
  49. Generative modeling by estimating gradients of the data distribution. Advances in neural information processing systems, 32, 2019.
  50. Improved techniques for training score-based generative models. Advances in neural information processing systems, 33:12438–12448, 2020.
  51. Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456, 2020.
  52. Contributions and challenges for network models in cognitive neuroscience. Nature Neuroscience, 2021. doi: 10.1038/s41593-021-00858-0. URL https://www.nature.com/articles/s41593-021-00858-0.
  53. Your diffusion model secretly knows the dimension of the data manifold, 2023.
  54. Fourier features let networks learn high frequency functions in low dimensional domains. Advances in Neural Information Processing Systems, 33:7537–7547, 2020.
  55. El niño–southern oscillation complexity. Nature, 559(7715):535–545, 2018.
  56. Turing, A. M. The chemical basis of morphogenesis. Bulletin of mathematical biology, 52:153–197, 1990.
  57. Vincent, P. A connection between score matching and denoising autoencoders. Neural computation, 23(7):1661–1674, 2011.
Citations (3)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets