Improving the Noise Estimation of Latent Neural Stochastic Differential Equations

• URL: http://arxiv.org/abs/2412.17499v1
• Date: Mon, 23 Dec 2024 11:56:35 GMT
• Title: Improving the Noise Estimation of Latent Neural Stochastic Differential Equations
• Authors: Linus Heck, Maximilian Gelbrecht, Michael T. Schaub, Niklas Boers,
• Abstract summary: Latent neural differential equations (SDEs) have recently emerged as a promising approach for learning generative models from time series data. We investigate this underestimation in detail and propose a straightforward solution: by including an explicit additional noise regularization in the loss function. We are able to learn a model that accurately captures the diffusion component of the data.
• Score: 4.64982780843177
• License:
• Abstract: Latent neural stochastic differential equations (SDEs) have recently emerged as a promising approach for learning generative models from stochastic time series data. However, they systematically underestimate the noise level inherent in such data, limiting their ability to capture stochastic dynamics accurately. We investigate this underestimation in detail and propose a straightforward solution: by including an explicit additional noise regularization in the loss function, we are able to learn a model that accurately captures the diffusion component of the data. We demonstrate our results on a conceptual model system that highlights the improved latent neural SDE's capability to model stochastic bistable dynamics.

Related papers

• Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural Dynamics [5.841659874892801]
  Time-varying linear state-space models are powerful tools for obtaining mathematically interpretable representations of neural signals. Existing methods for latent variable estimation are not robust to dynamical noise and system nonlinearity. We propose a probabilistic approach to latent variable estimation in decomposed models that improves robustness against dynamical noise.
  arXiv  Detail & Related papers  (2024-08-29T18:58:39Z)
• HyperSINDy: Deep Generative Modeling of Nonlinear Stochastic Governing Equations [5.279268784803583]
  We introduce HyperSINDy, a framework for modeling dynamics via a deep generative model of sparse governing equations from data. Once trained, HyperSINDy generates dynamics via a differential equation whose coefficients are driven by a white noise. In experiments, HyperSINDy recovers ground truth governing equations, with learnedity scaling to match that of the data.
  arXiv  Detail & Related papers  (2023-10-07T14:41:59Z)
• A Geometric Perspective on Diffusion Models [57.27857591493788]
  We inspect the ODE-based sampling of a popular variance-exploding SDE. We establish a theoretical relationship between the optimal ODE-based sampling and the classic mean-shift (mode-seeking) algorithm.
  arXiv  Detail & Related papers  (2023-05-31T15:33:16Z)
• Reservoir Computing with Error Correction: Long-term Behaviors of Stochastic Dynamical Systems [5.815325960286111]
  We propose a data-driven framework combining Reservoir Computing and Normalizing Flow to study this issue. We verify the effectiveness of the proposed framework in several experiments, including the Van der Pal, El Nino-Southern Oscillation simplified model, and Lorenz system.
  arXiv  Detail & Related papers  (2023-05-01T05:50:17Z)
• Capturing dynamical correlations using implicit neural representations [85.66456606776552]
  We develop an artificial intelligence framework which combines a neural network trained to mimic simulated data from a model Hamiltonian with automatic differentiation to recover unknown parameters from experimental data. In doing so, we illustrate the ability to build and train a differentiable model only once, which then can be applied in real-time to multi-dimensional scattering data.
  arXiv  Detail & Related papers  (2023-04-08T07:55:36Z)
• Learning and Inference in Sparse Coding Models with Langevin Dynamics [3.0600309122672726]
  We describe a system capable of inference and learning in a probabilistic latent variable model. We demonstrate this idea for a sparse coding model by deriving a continuous-time equation for inferring its latent variables via Langevin dynamics. We show that Langevin dynamics lead to an efficient procedure for sampling from the posterior distribution in the 'L0 sparse' regime, where latent variables are encouraged to be set to zero as opposed to having a small L1 norm.
  arXiv  Detail & Related papers  (2022-04-23T23:16:47Z)
• Closed-form Continuous-Depth Models [99.40335716948101]
  Continuous-depth neural models rely on advanced numerical differential equation solvers. We present a new family of models, termed Closed-form Continuous-depth (CfC) networks, that are simple to describe and at least one order of magnitude faster.
  arXiv  Detail & Related papers  (2021-06-25T22:08:51Z)
• Score-Based Generative Modeling through Stochastic Differential Equations [114.39209003111723]
  We present a differential equation that transforms a complex data distribution to a known prior distribution by injecting noise. A corresponding reverse-time SDE transforms the prior distribution back into the data distribution by slowly removing the noise. By leveraging advances in score-based generative modeling, we can accurately estimate these scores with neural networks. We demonstrate high fidelity generation of 1024 x 1024 images for the first time from a score-based generative model.
  arXiv  Detail & Related papers  (2020-11-26T19:39:10Z)
• Learning Partially Known Stochastic Dynamics with Empirical PAC Bayes [12.44342023476206]
  This paper presents a recipe to improve the prediction accuracy of such models in three steps. We observe in our experiments that this recipe effectively translates partial and noisy prior knowledge into an improved model fit.
  arXiv  Detail & Related papers  (2020-06-17T14:47:06Z)
• Multiplicative noise and heavy tails in stochastic optimization [62.993432503309485]
  empirical optimization is central to modern machine learning, but its role in its success is still unclear. We show that it commonly arises in parameters of discrete multiplicative noise due to variance. A detailed analysis is conducted in which we describe on key factors, including recent step size, and data, all exhibit similar results on state-of-the-art neural network models.
  arXiv  Detail & Related papers  (2020-06-11T09:58:01Z)
• Stochasticity in Neural ODEs: An Empirical Study [68.8204255655161]
  Regularization of neural networks (e.g. dropout) is a widespread technique in deep learning that allows for better generalization. We show that data augmentation during the training improves the performance of both deterministic and versions of the same model. However, the improvements obtained by the data augmentation completely eliminate the empirical regularization gains, making the performance of neural ODE and neural SDE negligible.
  arXiv  Detail & Related papers  (2020-02-22T22:12:56Z)

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.