NeurIPS 2022 accepted papers on Time series
26 of the 2,901 papers accepted at NeurIPS 2022 (0.9%) are on Time series, compared with 1.2% at NeurIPS 2021. They fall into 3 topics.
See NeurIPS 2022 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
- Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglement (36 citations)
- GT-GAN: General Purpose Time Series Synthesis with Generative Adversarial Networks (21 citations)
- On the difficulty of learning chaotic dynamics with RNNs (17 citations)
- Generating multivariate time series with COmmon Source CoordInated GAN (COSCI-GAN) (12 citations)
- C2FAR: Coarse-to-Fine Autoregressive Networks for Precise Probabilistic Forecasting (7 citations)
- Theoretical analysis of deep neural networks for temporally dependent observations (4 citations)
- Conformal Prediction with Temporal Quantile Adjustments (3 citations)
- Learning Deep Input-Output Stable Dynamics (2 citations)
- WaveBound: Dynamic Error Bounds for Stable Time Series Forecasting (2 citations)
- Efficient learning of nonlinear prediction models with time-series privileged information (1 citation)
- Detecting Abrupt Changes in Sequential Pairwise Comparison Data
- Causality Preserving Chaotic Transformation and Classification using Neurochaos Learning
and 2 more in the interactive map.
Long-term forecasting · 9 papers
- Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting (263 citations)
- SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction (246 citations)
- Earthformer: Exploring Space-Time Transformers for Earth System Forecasting (104 citations)
- FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting (104 citations)
- Learning to Reconstruct Missing Data from Spatiotemporal Graphs with Sparse Observations (18 citations)
- Learning Latent Seasonal-Trend Representations for Time Series Forecasting (5 citations)
- Multivariate Time-Series Forecasting with Temporal Polynomial Graph Neural Networks (3 citations)
- Time-Conditioned Dances with Simplicial Complexes: Zigzag Filtration Curve based Supra-Hodge Convolution Networks for Time-series Forecasting (2 citations)
- AZ-whiteness test: a test for signal uncorrelation on spatio-temporal graphs
