Dual reparametrized Variational Generative Model for Time-Series
Forecasting
- URL: http://arxiv.org/abs/2203.05766v1
- Date: Fri, 11 Mar 2022 06:02:16 GMT
- Title: Dual reparametrized Variational Generative Model for Time-Series
Forecasting
- Authors: Ziang Chen
- Abstract summary: This paper introduce dual reparametrized variational mechanisms on variational autoencoder (VAE) to prove the advance performance analytically.
The proven and experiment on multiple datasets illustrate, DualVDT, with a novel dual reparametrized structure, has the advanced performance both analytically and experimentally.
- Score: 0.0
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: This paper propose DualVDT, a generative model for Time-series forecasting.
Introduced dual reparametrized variational mechanisms on variational
autoencoder (VAE) to tighter the evidence lower bound (ELBO) of the model,
prove the advance performance analytically. This mechanism leverage the latent
score based generative model (SGM), explicitly denoising the perturbation
accumulated on latent vector through reverse time stochastic differential
equation and variational ancestral sampling. The posterior of denoised latent
distribution fused with dual reparametrized variational density. The KL
divergence in ELBO will reduce to reach the better results of the model. This
paper also proposed a latent attention mechanisms to extract multivariate
dependency explicitly. Build the local temporal dependency simultaneously in
factor wised through constructed local topology and temporal wised. The proven
and experiment on multiple datasets illustrate, DualVDT, with a novel dual
reparametrized structure, which denoise the latent perturbation through the
reverse dynamics combining local-temporal inference, has the advanced
performance both analytically and experimentally.
Related papers
- Robust Multivariate Time Series Forecasting against Intra- and Inter-Series Transitional Shift [40.734564394464556]
We present a unified Probabilistic Graphical Model to Jointly capturing intra-/inter-series correlations and modeling the time-variant transitional distribution.
We validate the effectiveness and efficiency of JointPGM through extensive experiments on six highly non-stationary MTS datasets.
arXiv Detail & Related papers (2024-07-18T06:16:03Z) - A Study of Posterior Stability for Time-Series Latent Diffusion [65.95306174480034]
We first explain that posterior collapse reduces latent diffusion to a VAE, making it less expressive.
We introduce the notion of dependency measures, showing that the latent variable sampled from the diffusion model loses control of the generation process.
We also analyze the causes of posterior collapse and introduce a new framework based on this analysis, which addresses the problem and supports a more expressive prior distribution.
arXiv Detail & Related papers (2024-05-22T21:54:12Z) - Wave function propagation in a two-dimensional paramagnetic
semiconductor from an impurity [0.0]
We simulate modifications to a model of a two-dimensional paramagnetic semiconductor called the half-BHZ model, also known as the QWZ model.
Our modifications include adding single and multiple impurities connected to the lattices or as a connection between the time-reversal pairs.
Our simulations showed the presence of scattering behavior associated with the infinite QWZ model topological states.
arXiv Detail & Related papers (2023-11-17T20:24:27Z) - Revisiting the Temporal Modeling in Spatio-Temporal Predictive Learning
under A Unified View [73.73667848619343]
We introduce USTEP (Unified S-TEmporal Predictive learning), an innovative framework that reconciles the recurrent-based and recurrent-free methods by integrating both micro-temporal and macro-temporal scales.
arXiv Detail & Related papers (2023-10-09T16:17:42Z) - Inference on Causal Effects of Interventions in Time using Gaussian
Processes [0.0]
This paper focuses on drawing inference on the causal impact of an intervention at a specific time point.
We operate on the interrupted time series framework and expand on approaches such as the synthetic control.
The developed models possess a high degree of flexibility posing very little limitations on the functional form.
arXiv Detail & Related papers (2022-10-06T12:10:57Z) - Towards Robust and Adaptive Motion Forecasting: A Causal Representation
Perspective [72.55093886515824]
We introduce a causal formalism of motion forecasting, which casts the problem as a dynamic process with three groups of latent variables.
We devise a modular architecture that factorizes the representations of invariant mechanisms and style confounders to approximate a causal graph.
Experiment results on synthetic and real datasets show that our three proposed components significantly improve the robustness and reusability of the learned motion representations.
arXiv Detail & Related papers (2021-11-29T18:59:09Z) - Estimation of Bivariate Structural Causal Models by Variational Gaussian
Process Regression Under Likelihoods Parametrised by Normalising Flows [74.85071867225533]
Causal mechanisms can be described by structural causal models.
One major drawback of state-of-the-art artificial intelligence is its lack of explainability.
arXiv Detail & Related papers (2021-09-06T14:52:58Z) - Loss function based second-order Jensen inequality and its application
to particle variational inference [112.58907653042317]
Particle variational inference (PVI) uses an ensemble of models as an empirical approximation for the posterior distribution.
PVI iteratively updates each model with a repulsion force to ensure the diversity of the optimized models.
We derive a novel generalization error bound and show that it can be reduced by enhancing the diversity of models.
arXiv Detail & Related papers (2021-06-09T12:13:51Z) - 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) - The temporal overfitting problem with applications in wind power curve
modeling [8.057262184815636]
We propose a new method to tackle the temporal overfitting problem.
Our specific application in this paper targets the power curve modeling in wind energy.
arXiv Detail & Related papers (2020-12-02T17:39:57Z)
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.