paper-with-me

Papers

Learning temporal evolution of probability distribution with Recurrent Neural Network

2018-01-01 · ICLR 2018 1 · Kyongmin Yeo, Igor Melnyk, Nam Nguyen, Eun Kyung Lee

We propose to tackle a time series regression problem by computing temporal evolution of a probability density function to provide a probabilistic forecast. A Recurrent Neural Network (RNN) based model is employed to learn a nonlinear operator for temporal evolution of a probability density function. We use a softmax layer for a numerical discretization of a smooth probability density functions, which transforms a function approximation problem to a classification task. Explicit and implicit regularization strategies are introduced to impose a smoothness condition on the estimated probability distribution. A Monte Carlo procedure to compute the temporal evolution of the distribution for a multiple-step forecast is presented. The evaluation of the proposed algorithm on three synthetic and two real data sets shows advantage over the compared baselines.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

General ClassificationregressionTime SeriesTime Series AnalysisTime Series Regression

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Deep Temporal-Recurrent-Replicated-Softmax for Topical Trends over Time

2017-11-15 · NAACL 2018 6 · Pankaj Gupta, Subburam Rajaram, Hinrich Schütze, Bernt Andrassy

Dynamic topic modeling facilitates the identification of topical trends over time in temporal collections of unstructured documents. We introduce a novel unsupervised neural dynamic topic model named as Recurrent Neural …

ArticlesDynamic Topic ModelingTopic Models

Learning the temporal evolution of multivariate densities via normalizing flows

2021-07-29 · Yubin Lu, Romit Maulik, Ting Gao, Felix Dietrich 외

In this work, we propose a method to learn multivariate probability distributions using sample path data from stochastic differential equations. Specifically, we consider temporally evolving probability distributions (e.…

Learning for Video Compression with Recurrent Auto-Encoder and Recurrent Probability Model

2020-06-24 · Ren Yang, Fabian Mentzer, Luc van Gool, Radu Timofte

The past few years have witnessed increasing interests in applying deep learning to video compression. However, the existing approaches compress a video frame with only a few number of reference frames, which limits thei…

DecoderMS-SSIMSSIMVideo Compression

Recurrent Flow Networks: A Recurrent Latent Variable Model for Density Modelling of Urban Mobility

2020-06-09 · ICML Workshop INNF 2021 7 · Daniele Gammelli, Filipe Rodrigues

Mobility-on-demand (MoD) systems represent a rapidly developing mode of transportation wherein travel requests are dynamically handled by a coordinated fleet of vehicles. Crucially, the efficiency of an MoD system highly…

Variational Inference

Recurrent Event Network : Global Structure Inference Over Temporal Knowledge Graph

2019-09-25 · Woojeong Jin, He Jiang, Meng Qu, Tong Chen 외

Modeling dynamically-evolving, multi-relational graph data has received a surge of interests with the rapid growth of heterogeneous event data. However, predicting future events on such data requires global structure inf…

Link PredictionTemporal Sequences