Latent Space Energy-based Neural ODEs

• URL: http://arxiv.org/abs/2409.03845v2
• Date: Wed, 05 Feb 2025 05:54:13 GMT
• Title: Latent Space Energy-based Neural ODEs
• Authors: Sheng Cheng, Deqian Kong, Jianwen Xie, Kookjin Lee, Ying Nian Wu, Yezhou Yang,
• Abstract summary: This paper introduces novel deep dynamical models designed to represent continuous-time sequences. We train the model using maximum likelihood estimation with Markov chain Monte Carlo. Experimental results on oscillating systems, videos and real-world state sequences (MuJoCo) demonstrate that our model with the learnable energy-based prior outperforms existing counterparts.
• Score: 73.01344439786524
• License:
• Abstract: This paper introduces novel deep dynamical models designed to represent continuous-time sequences. Our approach employs a neural emission model to generate each data point in the time series through a non-linear transformation of a latent state vector. The evolution of these latent states is implicitly defined by a neural ordinary differential equation (ODE), with the initial state drawn from an informative prior distribution parameterized by an Energy-based model (EBM). This framework is extended to disentangle dynamic states from underlying static factors of variation, represented as time-invariant variables in the latent space. We train the model using maximum likelihood estimation with Markov chain Monte Carlo (MCMC) in an end-to-end manner. Experimental results on oscillating systems, videos and real-world state sequences (MuJoCo) demonstrate that our model with the learnable energy-based prior outperforms existing counterparts, and can generalize to new dynamic parameterization, enabling long-horizon predictions.

Related papers

• Recurrent convolutional neural networks for non-adiabatic dynamics of quantum-classical systems [1.2972104025246092]
  We present a RNN model based on convolutional neural networks for modeling the nonlinear non-adiabatic dynamics of hybrid quantum-classical systems. validation studies show that the trained PARC model could reproduce the space-time evolution of a one-dimensional semi-classical Holstein model.
  arXiv  Detail & Related papers  (2024-12-09T16:23:25Z)
• Synthetic location trajectory generation using categorical diffusion models [50.809683239937584]
  Diffusion models (DPMs) have rapidly evolved to be one of the predominant generative models for the simulation of synthetic data. We propose using DPMs for the generation of synthetic individual location trajectories (ILTs) which are sequences of variables representing physical locations visited by individuals.
  arXiv  Detail & Related papers  (2024-02-19T15:57:39Z)
• 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)
• Anamnesic Neural Differential Equations with Orthogonal Polynomial Projections [6.345523830122166]
  We propose PolyODE, a formulation that enforces long-range memory and preserves a global representation of the underlying dynamical system. Our construction is backed by favourable theoretical guarantees and we demonstrate that it outperforms previous works in the reconstruction of past and future data.
  arXiv  Detail & Related papers  (2023-03-03T10:49:09Z)
• Free-Form Variational Inference for Gaussian Process State-Space Models [21.644570034208506]
  We propose a new method for inference in Bayesian GPSSMs. Our method is based on freeform variational inference via inducing Hamiltonian Monte Carlo. We show that our approach can learn transition dynamics and latent states more accurately than competing methods.
  arXiv  Detail & Related papers  (2023-02-20T11:34:16Z)
• Statistical and machine learning approaches for prediction of long-time excitation energy transfer dynamics [0.0]
  The objective here is to demonstrate whether models such as SARIMA, CatBoost, Prophet, convolutional and recurrent neural networks are able to bypass this requirement. Our results suggest that the SARIMA model can serve as a computationally inexpensive yet accurate way to predict long-time dynamics.
  arXiv  Detail & Related papers  (2022-10-25T16:50:26Z)
• 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)
• An Energy-Based Prior for Generative Saliency [62.79775297611203]
  We propose a novel generative saliency prediction framework that adopts an informative energy-based model as a prior distribution. With the generative saliency model, we can obtain a pixel-wise uncertainty map from an image, indicating model confidence in the saliency prediction. Experimental results show that our generative saliency model with an energy-based prior can achieve not only accurate saliency predictions but also reliable uncertainty maps consistent with human perception.
  arXiv  Detail & Related papers  (2022-04-19T10:51:00Z)
• Autoregressive Dynamics Models for Offline Policy Evaluation and Optimization [60.73540999409032]
  We show that expressive autoregressive dynamics models generate different dimensions of the next state and reward sequentially conditioned on previous dimensions. We also show that autoregressive dynamics models are useful for offline policy optimization by serving as a way to enrich the replay buffer.
  arXiv  Detail & Related papers  (2021-04-28T16:48:44Z)
• Liquid Time-constant Networks [117.57116214802504]
  We introduce a new class of time-continuous recurrent neural network models. Instead of declaring a learning system's dynamics by implicit nonlinearities, we construct networks of linear first-order dynamical systems. These neural networks exhibit stable and bounded behavior, yield superior expressivity within the family of neural ordinary differential equations.
  arXiv  Detail & Related papers  (2020-06-08T09:53:35Z)

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.