# Scientific Articles
We encourage you to also check out the time series work by the group behind GluonTS, ordered chronographically.

# 2023
* [Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecasting](https://arxiv.org/abs/2307.11494), *Marcel Kollovieh, Abdul Fatir Ansari, Michael Bohlke-Schneider, Jasper Zschiegner, Hao Wang, Yuyang Wang*, NeurIPS 2023
* [Learning Physical Models that Can Respect Conservation Laws](https://arxiv.org/pdf/2302.11002.pdf), *Derek Hansen, Danielle C. Maddix, Shima Alizadeh, Gaurav Gupta, Michael W. Mahoney*, ICML 2023
* Theoretical Guarantees of Learning Ensembling Strategies with Applications to Time Series Forecasting, *Hilaf Hasson, Danielle C. Maddix, Yuyang Wang, Gaurav Gupta, Youngsuk Park*, ICML 2023
* [Guiding continuous operator learning through Physics-based boundary constraints](https://arxiv.org/pdf/2212.07477.pdf), *Nadim Saad, Gaurav Gupta, Shima Alizadeh, Danielle C. Maddix*, ICLR 2023
* [Towards Robust Multivariate Time-Series Forecasting: Adversarial Attacks and Defense Mechanisms](https://arxiv.org/abs/2207.09572), *Linbo Liu, Youngsuk Park, Trong Nghia Hoang, Hilaf Hasson, Jun Huan*, ICLR 2023
* [Coherent Probabilistic Forecasting of Temporal Hierarchies](https://www.amazon.science/publications/coherent-probabilistic-forecasting-of-temporal-hierarchies), *Syama Sundar Rangapuram, Shubham Kapoor, Rajbir Singh Nirwan, Pedro Mercado, Yuyang Wang, Tim Januschowski, Michael Bohlke-Schneider*, AISTATS 2023
* [But are you sure? An uncertainty-aware perspective on explainable AI](https://www.amazon.science/publications/but-are-you-sure-an-uncertainty-aware-perspective-on-explainable-ai), *Charlie Marx, Youngsuk Park, Hilaf Hasson, Yuyang Wang, Stefano Ermon, Jun Huan*, AISTATS 2023
# 2022
* [Domain Adaptation for Time Series Forecasting via Attention Sharing](https://proceedings.mlr.press/v162/jin22d/jin22d.pdf), *Xiaoyong Jin, Youngsuk Park, Danielle C. Maddix, Hao Wang, Yuyang Wang*, ICML 2022
* [Robust Probabilistic Time Series Forecasting](https://proceedings.mlr.press/v151/yoon22a/yoon22a.pdf), *TaeHo Yoon, Youngsuk Park, Ernest Ryu, Yuyang Wang*, AISTATS 2022
* [Learning Quantile Functions without Quantile Crossing for Distribution-free Time Series Forecasting](https://proceedings.mlr.press/v151/park22a/park22a.pdf), *Youngsuk Park, Danielle C. Maddix, Francois-Xavier Aubet, Kelvin Kan, Jan Gasthaus, Yuyang Wang*, AISTATS 2022
* [Multivariate Quantile Function Forecaster](https://proceedings.mlr.press/v151/kan22a/kan22a.pdf), *Kelvin Kan , François-Xavier Aubet , Tim Januschowski, Youngsuk Park, Konstantinos Benidis, Lars Ruthotto, Jan Gasthaus*, AISTATS 2022
* [Deep Generative model with Hierarchical Latent Factors for Time Series Anomaly Detection](https://proceedings.mlr.press/v151/challu22a/challu22a.pdf), *Cristian Challu, Peihong Jiang, Ying Nian Wu, Laurent Callot*, AISTATS 2022
* [Testing Granger Non-Causality in Panels with Cross-Sectional Dependencies](https://proceedings.mlr.press/v151/minorics22a/minorics22a.pdf), *Lenon Minorics, Caner Turkmen, Patrick Bloebaum, David Kernert, Laurent Callot, Dominik Janzing*, AISTATS 2022
* [PSA-GAN: Progressive Self Attention GANs for Synthetic Time Series](https://arxiv.org/abs/2108.00981), *Paul Jeha, Michael Bohlke-Schneider, Pedro Mercado, Shubham Kapoor, Rajbir Singh Nirwan, Valentin Flunkert, Jan Gasthaus, Tim Januschowski*, ICLR 2022
* [Not All Domains Are Created Equal: Graph-Relational Domain Adaptation](https://arxiv.org/abs/2202.03628), *Zihao Xu, Hao He, Guang-He Lee, Yuyang Wang, Hao Wang*, ICLR 2022

# 2021

* [Forecasting with trees](https://www.sciencedirect.com/science/article/pii/S0169207021001679), *Tim Januschowski, Yuyang Wang, Kari Torkkola, Timo Erkkilä, Hilaf Hasson, Jan Gasthaus*, IJF 2021
* [Probabilistic Forecasting: A Level-Set Approach](https://proceedings.neurips.cc/paper/2021/file/32b127307a606effdcc8e51f60a45922-Paper.pdf), *Hilaf Hasson, Yuyang Wang, Tim Januschowski, and Jan Gasthaus*, NeurIPS 2021.
* [Deep Explicit Duration Switching Models for Time Series](https://papers.nips.cc/paper/2021/file/fb4c835feb0a65cc39739320d7a51c02-Paper.pdf), *Abdul Fatir Ansari, Konstantinos Benidis, Richard Kurle, Ali Caner Turkmen, Harold Soh, Alex Smola, Tim Januschowski*, NeurIPS 2021
* [Neural Flows: Efficient Alternative to Neural ODEs](https://papers.nips.cc/paper/2021/file/b21f9f98829dea9a48fd8aaddc1f159d-Paper.pdf), *Marin Biloš, Johanna Sommer, Syama Sundar Rangapuram, Tim Januschowski, Stephan Günnemann*, NeurIPS 2021
* [Detecting Anomalous Event Sequences with Temporal Point Processes](https://proceedings.neurips.cc/paper/2021/file/6faa8040da20ef399b63a72d0e4ab575-Paper.pdf), *Oleksandr Shchur, Ali Caner Turkmen, Tim Januschowski, Jan Gasthaus, Stephan Günnemann*, NeurIPS 2021
* [Online false discovery rate control for anomaly detection in time series](https://proceedings.neurips.cc/paper/2021/file/def130d0b67eb38b7a8f4e7121ed432c-Paper.pdf), *Quentin Rebjock, Baris Kurt, Tim Januschowski, Laurent Callot*, NeurIPS 2021
* Symmetry-breaking for Variational Bayesian Neural Networks, *Richard Kurle, Yuyang Wang, Tim Januschowski, Jan Gasthaus*, NeurIPS 2021 Workshop on Bayesian Deep Learning
* [GOPHER: Categorical probabilistic forecasting with graph structure via local continuous-time dynamics](https://proceedings.mlr.press/v163/wang22a/wang22a.pdf), *Alex Wang, Danielle C. Maddix, Yuyang Wang*, NeurIPS 2021 Workshop on ICBINB
* [Modeling Advection on Directed Graphs using Graph Matern Gaussian Processes for Traffic Flow](https://ml4physicalsciences.github.io/2021/files/NeurIPS_ML4PS_2021_13.pdf), *Danielle C. Maddix, Nadim Saad, Yuyang Wang*, NeurIPS 2021 Workshop on Machine Learning and The Physical Sciences
* Deep Generative model with Hierarchical Latent Factors for Timeseries Anomaly Detection, *Cristian Challu, Peihong Jiang, Ying Nian Wu, Laurent Callot*, NeurIPS 2021 Workshop on Deep Generative Models
* [Neural Temporal Point Processes: A Review](https://arxiv.org/abs/2104.03528), *Oleksandr Shchur, Ali Caner Türkmen, Tim Januschowski, Stephan Günnemann*, IJCAI 2021
* [Learning Quantile Functions without Quantile Crossing for Distribution-free Time Series Forecasting](https://arxiv.org/pdf/2111.06581), *Youngsuk Park, Danielle C. Maddix, François-Xavier Aubet, Kelvin Kan, Jan Gasthaus, Yuyang Wang*, ICML 2021 Workshop on Distribution-Free Uncertainty Quantification
* [Revisiting Dynamic Regret of Strongly Adaptive Methods](http://roseyu.com/time-series-workshop/submissions/2021/TSW-ICML2021_paper_41.pdf), *Dheeraj Baby, Hilaf Hasson, Yuyang Wang*, ICML Workshop on Time Series, 2021
* [A Study of Joint Graph Inference and Forecasting](https://arxiv.org/pdf/2109.04979), *Daniel Zügner, François-Xavier Aubet, Victor Garcia Satorras, Tim Januschowski, Stephan Günnemann, Jan Gasthaus*, ICML Workshop on Time Series, 2021
* [PSA-GAN: Progressive Self Attention GANs for Synthetic Time Series](https://arxiv.org/abs/2108.00981), *Jeha Paul, Bohlke-Schneider Michael, Mercado Pedro, Singh Nirwan Rajbir, Kapoor Shubham, Flunkert Valentin, Gasthaus Jan, Januschowski Tim*, ICML Workshop on Time Series, 2021
* [Variance Reduced Training with Stratified Sampling for Forecasting Models](http://proceedings.mlr.press/v139/lu21d/lu21d.pdf), *Yucheng Lu, Youngsuk Park, Lifan Chen, Yuyang Wang, Christopher De Sa, Dean Foster*, ICML 2021
* [End-to-end learning of coherent probabilistic forecasts for hierarchical time series](http://proceedings.mlr.press/v139/rangapuram21a/rangapuram21a.pdf), *Syama Sundar Rangapuram, Lucien D Werner, Konstantinos Benidis, Pedro Mercado, Jan Gasthaus, Tim Januschowski*, ICML 2021
* [Bridging Physics-based and Data-driven modeling for Learning Dynamical Systems](http://proceedings.mlr.press/v144/wang21a/wang21a.pdf), *Ray Wang, Danielle C. Maddix, Christos Faloutsos, Yuyang Wang, Rose Yu*, L4DC 2021
* Forecasting with Trees, *Tim Januschowski, Yuyang Wang, Kari Torkkola, Timo Erkkila, Hilaf Hasson, Jan Gasthaus*, International Journal of Forecasting (IJF) 2021
* [Forecasting: Theory and Practice](https://arxiv.org/abs/2012.03854), *Fotios Petroupolos et al and Tim Januschowski*, International Journal of Forecasting (IJF) 2021
* The M5 Competition: A Critial Appraisal, *Tim Januschowski, Jan Gasthaus, Yuyang Wang*, Foresight, 2021
* [Forecasting of intermittent and sparse time series: a unified probabilistic framework via deep renewal processes](https://journals.plos.org/plosone/article/authors?id=10.1371/journal.pone.0259764), *Caner Turkmen, Tim Januschowski, Yuyang Wang, Ali Taylan Cemgil*, PlosOne, 2021

# 2020
* [Deep Rao-Blackwellised Particle Filters for Time Series Forecasting](https://proceedings.neurips.cc/paper/2020/hash/afb0b97df87090596ae7c503f60bb23f-Abstract.html), *Richard Kurle, Syama Rangapuram, Emmanuel de Bezenac, Stepuhan Günnemann, Jan Gasthaus*, NeurIPS 2020
* [Normalizing Kalman Filters for Multivariate Time Series Analysis](https://papers.nips.cc/paper/2020/hash/1f47cef5e38c952f94c5d61726027439-Abstract.html), *Emmanuel de B\'{e}zenac, Syama S. Rangapuram, Konstantinos Benidis, Michael Bohlke-Schneider, Richard Kurle, Lorenzo Stella, Hilaf Hasson, Patrick Gallinari, Tim Januschowski*, NeurIPS 2020
* [Physics-based vs. Data-driven: A Benchmark Study on COVID-19 Forecasting](https://arxiv.org/pdf/2011.10616.pdf), *Ray Wang, Danielle C. Maddix, Christos Faloutsos, Yuyang Wang, Rose Yu*, **Best Paper Award**, NeurIPS 2020 Machine Learning in Public Health (MLPH) Workshop
* [Criteria for classifying forecasting methods](https://www.sciencedirect.com/science/article/pii/S0169207019301529), *Tim Januschowski, Jan Gasthaus, Yuyang Wang, David Salinas, Valentin Flunkert, Michael Bohlke-Schneider, Laurent Callot*, International Journal of Forecasting, 2020
* [DeepAR: Probabilistic forecasting with autoregressive recurrent networks](https://www.sciencedirect.com/science/article/pii/S0169207019301888), *David Salinas, Valentin Flunkert, Jan Gasthaus, Tim Januschowski*, International Journal of Forecasting, 2020
* [Anomaly Detection at Scale: The Case for Deep Distributional Time Series Models](https://arxiv.org/abs/2007.15541), 
*Fadhel Ayed, Lorenzo Stella, Tim Januschowski, Jan Gasthaus*, International Conference on Service-Oriented Computing, 2020
* [Forecasting Big Time Series: Theory and Practice](https://dl.acm.org/doi/10.1145/3366424.3383118), *Christos Faloutsos, Valentin Flunkert, Jan Gasthaus, Tim Januschowski, Yuyang Wang*, WWW 2020
* [Resilient neural forecasting systems](https://dl.acm.org/doi/pdf/10.1145/3399579.3399869), *Michael Bohlke-Schneider, Shubham Kapoor, Tim Januschowski*, DEEM 2020
* [Elastic machine learning algorithms in amazon sagemaker](https://dl.acm.org/doi/abs/10.1145/3318464.3386126), *Edo Liberty et al.*, SIGMOD 2020

# 2019 and Earlier
* [High-Dimensional Multivariate Forecasting with Low-Rank Gaussian Copula Processes](https://arxiv.org/abs/1910.03002), *David Salinas, Michael Bohlke-Schneider, Laurent Callot, Roberto Medico, Jan Gasthaus*, NeurIPS 2019
* [FastPoint: Scalable Deep Point Processes](https://ecmlpkdd2019.org/downloads/paper/861.pdf), *Ali Caner Turkmen, Yuyang Wang, Alex Smola*, **Best Paper Award**, ECML 2019
* [Forecasting Big Time Series: Theory and Practice](https://dl.acm.org/citation.cfm?id=3332289), *Christos Faloutsos, Jan Gasthaus, Tim Januschowski, Yuyang Wang*, KDD 2019
* [Classical and Contemporary Approaches to Big Time Series Forecasting](https://dl.acm.org/citation.cfm?id=3314033&dl=ACM&coll=DL), *Christos Faloutsos, Jan Gasthaus, Tim Januschowski, Yuyang Wang*, SIGMOD 2019
* [Deep factors for forecasting](http://proceedings.mlr.press/v97/wang19k.html), *Yuyang Wang, Alex Smola, Danielle C. Maddix, Jan Gasthaus, Dean Foster, Tim Januschowski*, ICML 2019
* [Probabilistic Forecasting with Spline Quantile Function RNNs](http://proceedings.mlr.press/v89/gasthaus19a.html), *Jan Gasthaus, Konstantinos Benidis, Yuyang Wang, Syama Sundar Rangapuram, David Salinas, Valentin Flunkert, Tim Januschowski*, AISTATS 2019
* Open-Source Forecasting Tools in Python, *Tim Januschowski, Jan Gasthaus, Yuyang Wang*, Foresight: The International Journal of Applied Forecasting, 2019
* [Deep state space models for time series forecasting](https://papers.nips.cc/paper/8004-deep-state-space-models-for-time-series-forecasting), *Syama Sundar Rangapuram, Matthias W. Seeger, Jan Gasthaus, Lorenzo Stella, Yuyang Wang, Tim Januschowski*, NeurIPS 2018
* [Forecasting big time series: old and new](http://www.vldb.org/pvldb/vol11/p2102-faloutsos.pdf), *Christos Faloutsos, Jan Gasthaus, Tim Januschowski, Yuyang Wang*, VLDB 2018
* Deep Learning for Forecasting: Current Trends and Challenges, *Januschowski, Tim and Gasthaus, Jan and Wang, Yuyang and Rangapuram, Syama Sundar and Callot, Laurent*, Foresight: The International Journal of Applied Forecasting, 2018
* Deep Learning for Forecasting, *Januschowski, Tim and Gasthaus, Jan and Wang, Yuyang and Rangapuram, Syama Sundar and Callot, Laurent*, Foresight: The International Journal of Applied Forecasting, 2018
* A Classification of Business Forecasting Problems, *Januschowski, Tim and Kolassa, Stephan*, Foresight: The International Journal of Applied Forecasting, 2018 
* [Probabilistic demand forecasting at scale](http://www.vldb.org/pvldb/vol10/p1694-schelter.pdf), *Joos-Hendrik Boese, Valentin Flunkert, Jan Gasthaus, Tim Januschowski, Dustin Lange, David Salinas, Sebastian Schelter, Matthias Seeger, Yuyang Wang*, VLDB 2017
* [Bayesian intermittent demand forecasting for large inventories](https://papers.nips.cc/paper/6313-bayesian-intermittent-demand-forecasting-for-large-inventories), *Matthias W. Seeger, David Salinas, Valentin Flunkert*, NeurIPS 2016