TACTiS: Transformer-Attentional Copulas for Time Series
The estimation of time-varying quantities is a fundamental component of decision making in fields such as healthcare and finance. However, the practical utility of such estimates is limited by how accurately they quantify predictive uncertainty. In this work, we address the problem of estimating the joint predictive distribution of high-dimensional multivariate time series. We propose a versatile method, based on the transformer architecture, that estimates joint distributions using an attention-based decoder that provably learns to mimic the properties of non-parametric copulas. The resulting model has several desirable properties: it can scale to hundreds of time series, supports both forecasting and interpolation, can handle unaligned and non-uniformly sampled data, and can seamlessly adapt to missing data during training. We demonstrate these properties empirically and show that our model produces state-of-the-art predictions on multiple real-world datasets.
Code (1)
Tasks
Decision MakingDecoderTime SeriesTime Series AnalysisTime Series ForecastingSimilar Papers 제목 키워드 기반
TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series
We introduce a new model for multivariate probabilistic time series prediction, designed to flexibly address a range of tasks including forecasting, interpolation, and their combinations. Building on copula theory, we pr…
Time SeriesTime Series PredictionVariational Bayes Estimation of Discrete-Margined Copula Models with Application to Time Series
We propose a new variational Bayes estimator for high-dimensional copulas with discrete, or a combination of discrete and continuous, margins. The method is based on a variational approximation to a tractable augmented p…
Time SeriesTime Series AnalysisSemi-parametric time series modelling with autocopulas
In this paper we present an application of the use of autocopulas for modelling financial time series showing serial dependencies that are not necessarily linear. The approach presented here is semi-parametric in that it…
Time SeriesTime Series AnalysisImpact of non-stationarity on estimating and modeling empirical copulas of daily stock returns
All too often measuring statistical dependencies between financial time series is reduced to a linear correlation coefficient. However this may not capture all facets of reality. We study empirical dependencies of daily …
Time SeriesTime Series AnalysisOptimal Copula Transport for Clustering Multivariate Time Series
This paper presents a new methodology for clustering multivariate time series leveraging optimal transport between copulas. Copulas are used to encode both (i) intra-dependence of a multivariate time series, and (ii) int…
ClusteringClustering Multivariate Time SeriesTime SeriesTime Series Analysis