no code implementations • 21 Mar 2022 • Deborah Sulem, Michele Donini, Muhammad Bilal Zafar, Francois-Xavier Aubet, Jan Gasthaus, Tim Januschowski, Sanjiv Das, Krishnaram Kenthapadi, Cedric Archambeau
In this work we propose a model-agnostic algorithm that generates counterfactual ensemble explanations for time series anomaly detection models.
This paper introduces a new approach for Multivariate Time Series forecasting that jointly infers and leverages relations among time series.
We propose Multivariate Quantile Function Forecaster (MQF$^2$), a global probabilistic forecasting method constructed using a multivariate quantile function and investigate its application to multi-horizon forecasting.
By learning a mapping from forecasting models to performance metrics, we show that our method PARETOSELECT is able to accurately select models from the Pareto front -- alleviating the need to train or evaluate many forecasting models for model selection.
The methods proposed in this article overcome short-comings of previous FDRC rules in the context of anomaly detection, in particular ensuring that power remains high even when the alternative is exceedingly rare (typical in anomaly detection) and the test statistics are serially dependent (typical in time series).
By recognizing the connection of our algorithm to random forests (RFs) and quantile regression forests (QRFs), we are able to prove consistency guarantees of our approach under mild assumptions on the underlying point estimator.
While classical time series forecasting considers individual time series in isolation, recent advances based on deep learning showed that jointly learning from a large pool of related time series can boost the forecasting accuracy.
We propose the Recurrent Explicit Duration Switching Dynamical System (RED-SDS), a flexible model that is capable of identifying both state- and time-dependent switching dynamics.
Modern time series corpora, in particular those coming from sensor-based data, exhibit characteristics that have so far not been adequately addressed in the literature on representation learning for time series.
We study a recent class of models which uses graph neural networks (GNNs) to improve forecasting in multivariate time series.
Automatically detecting anomalies in event data can provide substantial value in domains such as healthcare, DevOps, and information security.
no code implementations • • Emmanuel de Bézenac, Syama Sundar Rangapuram, Konstantinos Benidis, Michael Bohlke-Schneider, Richard Kurle, Lorenzo Stella, Hilaf Hasson, Patrick Gallinari, Tim Januschowski
This paper tackles the modelling of large, complex and multivariate time series panels in a probabilistic setting.
We propose a simple yet effective policy for the predictive auto-scaling of horizontally scalable applications running in cloud environments, where compute resources can only be added with a delay, and where the deployment throughput is limited.
Our method is amenable to streaming anomaly detection and scales to monitoring for anomalies on millions of time series.
In particular, we investigate the effectiveness of several forms of data binning, i. e. converting real-valued time series into categorical ones, when combined with feed-forward, recurrent neural networks, and convolution-based sequence models.
no code implementations • 21 Apr 2020 • Konstantinos Benidis, Syama Sundar Rangapuram, Valentin Flunkert, Bernie Wang, Danielle Maddix, Caner Turkmen, Jan Gasthaus, Michael Bohlke-Schneider, David Salinas, Lorenzo Stella, Laurent Callot, Tim Januschowski
Neural network based forecasting methods have become ubiquitous in large-scale industrial forecasting applications over the last years.
Intermittent demand, where demand occurrences appear sporadically in time, is a common and challenging problem in forecasting.
5 code implementations • 12 Jun 2019 • Alexander Alexandrov, Konstantinos Benidis, Michael Bohlke-Schneider, Valentin Flunkert, Jan Gasthaus, Tim Januschowski, Danielle C. Maddix, Syama Rangapuram, David Salinas, Jasper Schulz, Lorenzo Stella, Ali Caner Türkmen, Yuyang Wang
We introduce Gluon Time Series (GluonTS, available at https://gluon-ts. mxnet. io), a library for deep-learning-based time series modeling.
We provide both theoretical and empirical evidence for the soundness of our approach through a necessary and sufficient decomposition of exchangeable time series into a global and a local part.
We present a novel approach to probabilistic time series forecasting that combines state space models with deep learning.
We present a scalable and robust Bayesian inference method for linear state space models.