Path-minimizing Latent ODEs for improved extrapolation and inference
- URL: http://arxiv.org/abs/2410.08923v1
- Date: Fri, 11 Oct 2024 15:50:01 GMT
- Title: Path-minimizing Latent ODEs for improved extrapolation and inference
- Authors: Matt L. Sampson, Peter Melchior,
- Abstract summary: Latent ODE models provide flexible descriptions of dynamic systems, but they can struggle with extrapolation and predicting complicated non-linear dynamics.
In this paper we exploit this dichotomy by encouraging time-independent latent representations.
By replacing the common variational penalty in latent space with an $ell$ penalty on the path length of each system, the models learn data representations that can easily be distinguished from those of systems with different configurations.
This results in faster training, smaller models, more accurate and long-time extrapolation compared to the baseline ODE models with GRU, RNN, and LSTM/decoders on tests with
- Score: 0.0
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Latent ODE models provide flexible descriptions of dynamic systems, but they can struggle with extrapolation and predicting complicated non-linear dynamics. The latent ODE approach implicitly relies on encoders to identify unknown system parameters and initial conditions, whereas the evaluation times are known and directly provided to the ODE solver. This dichotomy can be exploited by encouraging time-independent latent representations. By replacing the common variational penalty in latent space with an $\ell_2$ penalty on the path length of each system, the models learn data representations that can easily be distinguished from those of systems with different configurations. This results in faster training, smaller models, more accurate interpolation and long-time extrapolation compared to the baseline ODE models with GRU, RNN, and LSTM encoder/decoders on tests with damped harmonic oscillator, self-gravitating fluid, and predator-prey systems. We also demonstrate superior results for simulation-based inference of the Lotka-Volterra parameters and initial conditions by using the latents as data summaries for a conditional normalizing flow. Our change to the training loss is agnostic to the specific recognition network used by the decoder and can therefore easily be adopted by other latent ODE models.
Related papers
- Reduced Order Modeling with Shallow Recurrent Decoder Networks [5.686433280542813]
SHRED-ROM is a robust decoding-only strategy that encodes the numerically unstable approximation of an inverse.
We show that SHRED-ROM accurately reconstructs the state dynamics for new parameter values starting from limited fixed or mobile sensors.
arXiv Detail & Related papers (2025-02-15T23:41:31Z) - No Equations Needed: Learning System Dynamics Without Relying on Closed-Form ODEs [56.78271181959529]
This paper proposes a conceptual shift to modeling low-dimensional dynamical systems by departing from the traditional two-step modeling process.
Instead of first discovering a closed-form equation and then analyzing it, our approach, direct semantic modeling, predicts the semantic representation of the dynamical system.
Our approach not only simplifies the modeling pipeline but also enhances the transparency and flexibility of the resulting models.
arXiv Detail & Related papers (2025-01-30T18:36:48Z) - Sparse identification of nonlinear dynamics and Koopman operators with Shallow Recurrent Decoder Networks [3.1484174280822845]
We present S Identification of Dynamics with SHallow REcurrent Decoder networks (SINDy-SHRED), a method to jointly solve the sensing and model identification problems.
SINDy-SHRED uses Gated Recurrent Units (GRUs) to model the temporal sequence of sensor measurements along with shallow decoder network to reconstruct the full field from the latent state space.
We conduct a systematic experimental study including synthetic PDE data, real-world sensor measurements for sea surface temperature, and direct video data.
arXiv Detail & Related papers (2025-01-23T02:18:13Z) - Balanced Neural ODEs: nonlinear model order reduction and Koopman operator approximations [0.0]
Variational Autoencoders (VAEs) are a powerful framework for learning latent representations of reduced dimensionality.
Neural ODEs excel in learning transient system dynamics.
We show that standard Latent ODEs struggle with dimensionality reduction in systems with time-varying inputs.
arXiv Detail & Related papers (2024-10-14T05:45:52Z) - On the Trajectory Regularity of ODE-based Diffusion Sampling [79.17334230868693]
Diffusion-based generative models use differential equations to establish a smooth connection between a complex data distribution and a tractable prior distribution.
In this paper, we identify several intriguing trajectory properties in the ODE-based sampling process of diffusion models.
arXiv Detail & Related papers (2024-05-18T15:59:41Z) - Foundational Inference Models for Dynamical Systems [5.549794481031468]
We offer a fresh perspective on the classical problem of imputing missing time series data, whose underlying dynamics are assumed to be determined by ODEs.
We propose a novel supervised learning framework for zero-shot time series imputation, through parametric functions satisfying some (hidden) ODEs.
We empirically demonstrate that one and the same (pretrained) recognition model can perform zero-shot imputation across 63 distinct time series with missing values.
arXiv Detail & Related papers (2024-02-12T11:48:54Z) - Reflected Diffusion Models [93.26107023470979]
We present Reflected Diffusion Models, which reverse a reflected differential equation evolving on the support of the data.
Our approach learns the score function through a generalized score matching loss and extends key components of standard diffusion models.
arXiv Detail & Related papers (2023-04-10T17:54:38Z) - 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) - Capturing Actionable Dynamics with Structured Latent Ordinary
Differential Equations [68.62843292346813]
We propose a structured latent ODE model that captures system input variations within its latent representation.
Building on a static variable specification, our model learns factors of variation for each input to the system, thus separating the effects of the system inputs in the latent space.
arXiv Detail & Related papers (2022-02-25T20:00:56Z) - Neural ODE Processes [64.10282200111983]
We introduce Neural ODE Processes (NDPs), a new class of processes determined by a distribution over Neural ODEs.
We show that our model can successfully capture the dynamics of low-dimensional systems from just a few data-points.
arXiv Detail & Related papers (2021-03-23T09:32:06Z) - Anomaly Detection of Time Series with Smoothness-Inducing Sequential
Variational Auto-Encoder [59.69303945834122]
We present a Smoothness-Inducing Sequential Variational Auto-Encoder (SISVAE) model for robust estimation and anomaly detection of time series.
Our model parameterizes mean and variance for each time-stamp with flexible neural networks.
We show the effectiveness of our model on both synthetic datasets and public real-world benchmarks.
arXiv Detail & Related papers (2021-02-02T06:15:15Z)
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.