Temporal Latent Auto-Encoder: A Method for Probabilistic Multivariate Time Series Forecasting

TL;DR: Wang et al. as mentioned in this paper proposed a novel neural network architecture and applied it for the time series forecasting problem, wherein they conduct sample convolution and interaction at multiple resolutions for temporal modeling.

TL;DR: A hierarchical graph structure cooperated with the dilated convolution is provided to capture the scale-specific correlations among time series and a series of adjacency matrices are constructed under a recurrent manner to represent the evolving correlations at each layer.

TL;DR: Li et al. as discussed by the authors proposed Probformer, a Transformer-based forecasting model for EV charging load forecasting, and further extended it to MetaProbformer, which is a meta-learning based forecasting framework.

TL;DR: In this article, an Optimized Gradient Boosting Regressor (OGBR) was proposed, which has been optimized by a modified version of the Particle Swarm Optimization (PSO) for fast parameter optimization.

TL;DR: This paper proposed a simple network architecture based solely on an attention mechanism, dispensing with recurrence and convolutions entirely and achieved state-of-the-art performance on English-to-French translation.

Abstract: The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the WMT 2014 English-to-German translation task, improving over the existing best results, including ensembles by over 2 BLEU. On the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.8 after training for 3.5 days on eight GPUs, a small fraction of the training costs of the best models from the literature. We show that the Transformer generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.

TL;DR: A new framework for estimating generative models via an adversarial process, in which two models are simultaneously train: a generative model G that captures the data distribution and a discriminative model D that estimates the probability that a sample came from the training data rather than G.

TL;DR: A stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case is introduced.