1. This result **extends** your **machine learning surrogate models** by proving that complex dynamical systems with p parameters can be rigorously identified and reconstructed using exactly 2p+1 random features, even under non-i.i.d. and state-dependent noise.

Adversarial Debate Score

33% survival rate under critique

Supporting Research Papers

• A machine learning framework for uncovering stochastic nonlinear dynamics from noisy data

  Modeling real-world systems requires accounting for noise - whether it arises from unpredictable fluctuations in financial markets, irregular rhythms in biological systems, or environmental variabilit...

• An Introduction to Sparse Identification of Nonlinear Dynamics for Engineering Applications

  Many engineering problems involve phenomena whose governing equations are poorly characterized or only partially known. Surrogate modeling techniques such as neural networks can capture the behavior o...

• Factorized Neural Implicit DMD for Parametric Dynamics

  A data-driven, model-free approach to modeling the temporal evolution of physical systems mitigates the need for explicit knowledge of the governing equations. Even when physical priors such as partia...

• Joint Identification of Linear Dynamics and Noise Covariance via Distributional Estimation

  In this paper, we propose a novel framework for the joint identification of system dynamics and noise covariance in linear systems, under general noise distributions beyond Gaussian. Specifically, we ...

• Framing local structural identifiability and observability in terms of parameter-state symmetries

  We introduce a subclass of Lie symmetries, called parameter-state symmetries, to analyse the local structural identifiability and observability of mechanistic models consisting of state-dependent ODEs...

Computational Validation

Formal Verification

Source