NeurIPS 2018 accepted papers on Time series
15 of the 1,008 papers accepted at NeurIPS 2018 (1.5%) are on Time series, compared with 1.2% at NeurIPS 2017. They fall into 4 topics.
See NeurIPS 2018 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 · 11 papers
- Deep State Space Models for Time Series Forecasting (429 citations)
- BRITS: Bidirectional Recurrent Imputation for Time Series (372 citations)
- Multivariate Time Series Imputation with Generative Adversarial Networks (291 citations)
- Complex Gated Recurrent Neural Networks (39 citations)
- Multiple Instance Learning for Efficient Sequential Data Classification on Resource-constrained Devices (27 citations)
- Bayesian Alignments of Warped Multi-Output Gaussian Processes (11 citations)
- Dimensionality Reduction for Stationary Time Series via Stochastic Nonconvex Optimization (6 citations)
- Deep Poisson gamma dynamical systems (2 citations)
- Forecasting Treatment Responses Over Time Using Recurrent Marginal Structural Networks
- Parsimonious Quantile Regression of Financial Asset Tail Dynamics via Sequential Learning
- Safe Active Learning for Time-Series Modeling with Gaussian Processes
Foundation models for time series · 2 papers
Long-term forecasting · 1 paper
Anomaly detection · 1 paper
- Precision and Recall for Time Series (38 citations)
