arXiv (Cornell University) · 2019 · 20 citations · 54 references
EngineeringComputer SciencePhysicsDynamical SystemsMachine LearningStochastic ProcessesDeep LearningMarkov ChainsMarkov ProcessesState-space ModelingState-space ModelsState-space RepresentationLatent Space EmbeddingLatent Space ExplorationLatent Space ModelsLong-time BehaviorReversible Markov ChainsStochastic Dynamical Systems
The long-timescale behavior of complex dynamical systems can be described by linear Markov or Koopman models in a suitable latent space. Recent variational approaches allow the latent space representation and the linear dynamical model to be optimized via unsupervised machine learning methods. Incorporation of physical constraints such as time-reversibility or stochasticity into the dynamical model has been established for a linear, but not for arbitrarily nonlinear (deep learning) representations of the latent space. Here we develop theory and methods for deep learning Markov and Koopman models that can bear such physical constraints. We prove that the model is an universal approximator for reversible Markov processes and that it can be optimized with either maximum likelihood or the variational approach of Markov processes (VAMP). We demonstrate that the model performs equally well for equilibrium and systematically better for biased data compared to existing approaches, thus providing a tool to study the long-timescale processes of dynamical systems.
54
Spectral analysis of nonlinear flows
Clarence W. Rowley, Igor Mezić, Shervin Bagheri et al. · Journal of Fluid Mechanics · 2009 · 2.3K citations
Markov models of molecular kinetics: Generation and validation
Jan-Hendrik Prinz, Hao Wu, Marco Sarich et al. · The Journal of Chemical Physics · 2011 · 1.3K citations · Full text
Natural Sciences, Chemistry, Physics +15