Related papers: One Model to Forecast Them All and in Entity Distr…

Nowadays, with the unprecedented penetration of renewable distributed energy resources (DERs), the necessity of an efficient energy forecasting model is more demanding than before. Generally, forecasting models are trained using observed…

A key advance in learning generative models is the use of amortized inference distributions that are jointly trained with the models. We find that existing training objectives for variational autoencoders can lead to inaccurate amortized…

Power systems engineers are actively developing larger power plants out of photovoltaics imposing some major challenges which include its intermittent power generation and its poor dispatchability. The issue is that PV is a variable…

Forecasting short-term motion of nearby vehicles presents an inherently challenging issue as the space of their possible future movements is not strictly limited to a set of single trajectories. Recently proposed techniques that demonstrate…

We build a time-causal variational autoencoder (TC-VAE) for robust generation of financial time series data. Our approach imposes a causality constraint on the encoder and decoder networks, ensuring a causal transport from the real market…

Purpose: Handling heterogeneous and mixed data types has become increasingly critical with the exponential growth in real-world databases. While deep generative models attempt to merge diverse data views into a common latent space, they…

As an important problem in causal inference, we discuss the estimation of treatment effects (TEs). Representing the confounder as a latent variable, we propose Intact-VAE, a new variant of variational autoencoder (VAE), motivated by the…

The Variational Autoencoder (VAE) is a powerful architecture capable of representation learning and generative modeling. When it comes to learning interpretable (disentangled) representations, VAE and its variants show unparalleled…

Multi-view data from the same source often exhibit correlation. This is mirrored in correlation between the latent spaces of separate variational autoencoders (VAEs) trained on each data-view. A multi-view VAE approach is proposed that…

This paper develops probabilistic PV forecasters by taking advantage of recent breakthroughs in deep learning. It tailored forecasting tool, named encoder-decoder, is implemented to compute intraday multi-output PV quantiles forecasts to…

Due to the non-stationary nature, the distribution of real-world multivariate time series (MTS) changes over time, which is known as distribution drift. Most existing MTS forecasting models greatly suffer from distribution drift and degrade…

The next decade will usher in a profound transformation of wireless communication, driven by the ever-increasing demand for data-intensive applications and the rapid adoption of emerging technologies. To fully unlock the potential of 5G and…

Extracting compact, physically interpretable representations from high-dimensional scientific data is a persistent challenge due to the complex, nonlinear structures inherent in physical systems. We propose a Gaussian Mixture Variational…

With the increasingly widespread deployment of generative models, there is a mounting need for a deeper understanding of their behaviors and limitations. In this paper, we expose the limitations of Variational Autoencoders (VAEs), which…

As a result of increasing population and globalization, the demand for energy has greatly risen. Therefore, accurate energy consumption forecasting has become an essential prerequisite for government planning, reducing power wastage and…

We consider the closely related problems of sampling from a distribution known up to a normalizing constant, and estimating said normalizing constant. We show how variational autoencoders (VAEs) can be applied to this task. In their…

Data-driven modeling is useful for reconstructing nonlinear dynamical systems when the underlying process is unknown or too expensive to compute. Having reliable uncertainty assessment of the forecast enables tools to be deployed to predict…

Recent studies have explored the use of deep generative models of speech spectra based of variational autoencoders (VAEs), combined with unsupervised noise models, to perform speech enhancement. These studies developed iterative algorithms…

Predicting future frames for a video sequence is a challenging generative modeling task. Promising approaches include probabilistic latent variable models such as the Variational Auto-Encoder. While VAEs can handle uncertainty and model…

Optimization of rotating electrical machines is both time- and computationally expensive. Because of the different parametrization, design optimization is commonly executed separately for each machine technology. In this paper, we present…