NeurIPS 2021 accepted papers on Time series
30 of the 2,508 papers accepted at NeurIPS 2021 (1.2%) are on Time series, compared with 1.0% at NeurIPS 2020. They fall into 4 topics.
See NeurIPS 2021 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 · 24 papers
- Combining Recurrent, Convolutional, and Continuous-time Models with Linear State Space Layers (83 citations)
- CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation (75 citations)
- Revisiting Time Series Outlier Detection: Definitions and Benchmarks (53 citations)
- Conformal Time-series Forecasting (33 citations)
- Neural Flows: Efficient Alternative to Neural ODEs (25 citations)
- Disentangling Identifiable Features from Noisy Data with Structured Nonlinear ICA (19 citations)
- Adjusting for Autocorrelated Errors in Neural Networks for Time Series (16 citations)
- Machine learning structure preserving brackets for forecasting irreversible processes (10 citations)
- Change Point Detection via Multivariate Singular Spectrum Analysis (6 citations)
- Coresets for Time Series Clustering (6 citations)
- DeepSITH: Efficient Learning via Decomposition of What and When Across Time Scales (5 citations)
- MixSeq: Connecting Macroscopic Time Series Forecasting with Microscopic Time Series Data (5 citations)
and 12 more in the interactive map.
