NeurIPS 2019 accepted papers on Time series
20 of the 1,429 papers accepted at NeurIPS 2019 (1.4%) are on Time series, compared with 1.5% at NeurIPS 2018. They fall into 3 topics.
See NeurIPS 2019 in the interactive map
Submitting to NeurIPS? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Causal and generative time series · 14 papers
- Time-series Generative Adversarial Networks (511 citations)
- Latent Ordinary Differential Equations for Irregularly-Sampled Time Series (238 citations)
- GRU-ODE-Bayes: Continuous Modeling of Sporadically-Observed Time Series (167 citations)
- Shape and Time Distortion Loss for Training Deep Time Series Forecasting Models (104 citations)
- Fully Neural Network based Model for General Temporal Point Processes (77 citations)
- U-Time: A Fully Convolutional Network for Time Series Segmentation Applied to Sleep Staging (60 citations)
- High-dimensional multivariate forecasting with low-rank Gaussian Copula Processes (38 citations)
- Sequential Neural Processes (37 citations)
- Uncertainty on Asynchronous Time Event Prediction (24 citations)
- Learning low-dimensional state embeddings and metastable clusters from time series data (9 citations)
- Nonparametric Regressive Point Processes Based on Conditional Gaussian Processes (9 citations)
- Unsupervised Discovery of Temporal Structure in Noisy Data with Dynamical Components Analysis (9 citations)
and 2 more in the interactive map.
Foundation models for time series · 3 papers
- Unsupervised Scalable Representation Learning for Multivariate Time Series (232 citations)
- Learning Representations for Time Series Clustering (98 citations)
- Diffeomorphic Temporal Alignment Nets (21 citations)
Long-term forecasting · 3 papers
- Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting (1,086 citations)
- Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecasting (95 citations)
- Shallow RNN: Accurate Time-series Classification on Resource Constrained Devices (18 citations)
