Learning Neural Contracting Dynamics: Extended Linearization and Global Guarantees

• URL: http://arxiv.org/abs/2402.08090v4
• Date: Wed, 08 Jan 2025 03:08:11 GMT
• Title: Learning Neural Contracting Dynamics: Extended Linearization and Global Guarantees
• Authors: Sean Jaffe, Alexander Davydov, Deniz Lapsekili, Ambuj Singh, Francesco Bullo,
• Abstract summary: We present Extended Linearized Contracting Dynamics (ELCD), the first neural network-based dynamical system with global contractivity guarantees in arbitrary metrics. In its most basic form, ELCD is guaranteed to be (i) globally exponentially stable, (ii) equilibrium contracting, and (iii) globally contracting with respect to some metric. We demonstrate the performance of ELCD on the high dimensional LASA, multi-link pendulum, and Rosenbrock datasets.
• Score: 43.71741802581781
• License:
• Abstract: Global stability and robustness guarantees in learned dynamical systems are essential to ensure well-behavedness of the systems in the face of uncertainty. We present Extended Linearized Contracting Dynamics (ELCD), the first neural network-based dynamical system with global contractivity guarantees in arbitrary metrics. The key feature of ELCD is a parametrization of the extended linearization of the nonlinear vector field. In its most basic form, ELCD is guaranteed to be (i) globally exponentially stable, (ii) equilibrium contracting, and (iii) globally contracting with respect to some metric. To allow for contraction with respect to more general metrics in the data space, we train diffeomorphisms between the data space and a latent space and enforce contractivity in the latent space, which ensures global contractivity in the data space. We demonstrate the performance of ELCD on the high dimensional LASA, multi-link pendulum, and Rosenbrock datasets.

Related papers

• World-Consistent Data Generation for Vision-and-Language Navigation [52.08816337783936]
  Vision-and-Language Navigation (VLN) is a challenging task that requires an agent to navigate through photorealistic environments following natural-language instructions. One main obstacle existing in VLN is data scarcity, leading to poor generalization performance over unseen environments. We propose the world-consistent data generation (WCGEN), an efficacious data-augmentation framework satisfying both diversity and world-consistency.
  arXiv  Detail & Related papers  (2024-12-09T11:40:54Z)
• Stability properties of gradient flow dynamics for the symmetric low-rank matrix factorization problem [22.648448759446907]
  We show that a low-rank factorization serves as a building block in many learning tasks. We offer new insight into the shape of the trajectories associated with local search parts of the dynamics.
  arXiv  Detail & Related papers  (2024-11-24T20:05:10Z)
• Learning Controlled Stochastic Differential Equations [61.82896036131116]
  This work proposes a novel method for estimating both drift and diffusion coefficients of continuous, multidimensional, nonlinear controlled differential equations with non-uniform diffusion. We provide strong theoretical guarantees, including finite-sample bounds for (L2), (Linfty), and risk metrics, with learning rates adaptive to coefficients' regularity. Our method is available as an open-source Python library.
  arXiv  Detail & Related papers  (2024-11-04T11:09:58Z)
• Inferring stability properties of chaotic systems on autoencoders' latent spaces [4.266376725904727]
  In chaotic systems and turbulence, convolutional autoencoders and echo state networks (CAE-ESN) successfully forecast the dynamics. We show that the CAE-ESN model infers the invariant stability properties and the geometry of the space vectors in the low-dimensional manifold. This work opens up new opportunities for inferring the stability of high-dimensional chaotic systems in latent spaces.
  arXiv  Detail & Related papers  (2024-10-23T16:25:36Z)
• Stability analysis of chaotic systems in latent spaces [4.266376725904727]
  We show that a latent-space approach can infer the solution of a chaotic partial differential equation. It can also predict the stability properties of the physical system.
  arXiv  Detail & Related papers  (2024-10-01T08:09:14Z)
• Ensuring Both Positivity and Stability Using Sector-Bounded Nonlinearity for Systems with Neural Network Controllers [0.0]
  We present a stability theorem that demonstrates the global exponential stability of linear systems under fully connected FFNN control. Our approach effectively addresses the challenge of ensuring stability in highly nonlinear systems. We showcase the practical applicability of our methodology through its implementation in a linear system managed by a FFNN trained on output feedback controller data.
  arXiv  Detail & Related papers  (2024-06-18T16:05:57Z)
• Convergence of mean-field Langevin dynamics: Time and space discretization, stochastic gradient, and variance reduction [49.66486092259376]
  The mean-field Langevin dynamics (MFLD) is a nonlinear generalization of the Langevin dynamics that incorporates a distribution-dependent drift. Recent works have shown that MFLD globally minimizes an entropy-regularized convex functional in the space of measures. We provide a framework to prove a uniform-in-time propagation of chaos for MFLD that takes into account the errors due to finite-particle approximation, time-discretization, and gradient approximation.
  arXiv  Detail & Related papers  (2023-06-12T16:28:11Z)
• Disentangled Federated Learning for Tackling Attributes Skew via Invariant Aggregation and Diversity Transferring [104.19414150171472]
  Attributes skews the current federated learning (FL) frameworks from consistent optimization directions among the clients. We propose disentangled federated learning (DFL) to disentangle the domain-specific and cross-invariant attributes into two complementary branches. Experiments verify that DFL facilitates FL with higher performance, better interpretability, and faster convergence rate, compared with SOTA FL methods.
  arXiv  Detail & Related papers  (2022-06-14T13:12:12Z)
• Towards Robust Unsupervised Disentanglement of Sequential Data -- A Case Study Using Music Audio [17.214062755082065]
  Disentangled sequential autoencoders (DSAEs) represent a class of probabilistic graphical models. We show that the vanilla DSAE suffers from being sensitive to the choice of model architecture and capacity of the dynamic latent variables. We propose TS-DSAE, a two-stage training framework that first learns sequence-level prior distributions.
  arXiv  Detail & Related papers  (2022-05-12T04:11:25Z)
• Understanding Overparameterization in Generative Adversarial Networks [56.57403335510056]
  Generative Adversarial Networks (GANs) are used to train non- concave mini-max optimization problems. A theory has shown the importance of the gradient descent (GD) to globally optimal solutions. We show that in an overized GAN with a $1$-layer neural network generator and a linear discriminator, the GDA converges to a global saddle point of the underlying non- concave min-max problem.
  arXiv  Detail & Related papers  (2021-04-12T16:23:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.