Learning temporal evolution of probability distribution with Recurrent Neural Network

Kyongmin Yeo, Igor Melnyk, Nam Nguyen, Eun Kyung Lee

Abstract: 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.

TL;DR: Proposed RNN-based algorithm to estimate predictive distribution in one- and multi-step forecasts in time series prediction problems

Keywords: predictive distribution estimation, probabilistic RNN, uncertainty in time series prediction