Manifold learning for parameter reduction

Abstract

Large scale dynamical systems (e.g. many nonlinear coupled differential equations) can often be summarized in terms of only a few state variables (a few equations), a trait that reduces complexity and facilitates exploration of behavioral aspects of otherwise intractable models. High model dimensionality and complexity makes symbolic, pen--and--paper model reduction tedious and impractical, a difficulty addressed by recently developed frameworks that computerize reduction. Symbolic work has the benefit, however, of identifying both reduced state variables and parameter combinations that matter most (effective parameters, "inputs"); whereas current computational reduction schemes leave the parameter reduction aspect mostly unaddressed. As the interest in mapping out and optimizing complex input--output relations keeps growing, it becomes clear that combating the curse of dimensionality also requires efficient schemes for input space exploration and reduction. Here, we explore systematic, data-driven parameter reduction by means of effective parameter identification, starting from current nonlinear manifold-learning techniques enabling state space reduction. Our approach aspires to extend the data-driven determination of effective state variables with the data-driven discovery of effective model parameters, and thus to accelerate the exploration of high-dimensional parameter spaces associated with complex models.

References in corpus (10)

• Universally Sloppy Parameter Sensitivities in Systems Biology
• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
• Active subspace methods in theory and practice: applications to kriging surfaces
• The geometry of nonlinear least squares with applications to sloppy models and optimization
• Why are nonlinear fits so challenging?
• The sloppy model universality class and the Vandermonde matrix
• iMapD: intrinsic Map Dynamics exploration for uncharted effective free energy landscapes
• Diffusion maps for changing data
• A near-stationary subspace for ridge approximation
• On the correspondence between thermodynamics and inference

Cited by in corpus (17)

• Explainable Machine Learning for Scientific Insights and Discoveries
• Coarse-scale PDEs from fine-scale observations via machine learning
• Symplectic Neural Networks in Taylor Series Form for Hamiltonian Systems
• Constructing coarse-scale bifurcation diagrams from spatio-temporal observations of microscopic simulations: A parsimonious machine learning approach
• A quantitative framework for exploring exit strategies from the COVID-19 lockdown
• Data-driven Control of Agent-based Models: an Equation/Variable-free Machine Learning Approach
• Discovering Conservation Laws using Optimal Transport and Manifold Learning
• Multi-fidelity data fusion through parameter space reduction with applications to automotive engineering
• From partial data to out-of-sample parameter and observation estimation with Diffusion Maps and Geometric Harmonics
• Learning normal form autoencoders for data-driven discovery of universal,parameter-dependent governing equations
• Spectral Discovery of Jointly Smooth Features for Multimodal Data
• Global and Local Reduced Models for Interacting, Heterogeneous Agents
• Learning the Latent dynamics of Fluid flows from High-Fidelity Numerical Simulations using Parsimonious Diffusion Maps
• Kernel-based parameter estimation of dynamical systems with unknown observation functions
• A Lipschitz Matrix for Parameter Reduction in Computational Science
• Some manifold learning considerations towards explicit model predictive control
• On the Parameter Combinations That Matter and on Those That do Not