Research map / Time series / Causal and generative time series
Multivariate Probabilistic Time Series Forecasting via Conditioned Normalizing Flows
Kashif Rasul, Abdul-Saboor Sheikh, Ingmar Schuster, Urs M Bergmann, Roland Vollgraf
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Replace Real-NVP with MAF in the LSTM-conditioned flow (ablation) | LSTM-Real-NVP · Solar | CRPS_sum: 0.331 -> 0.315 | Improved |
| Replace Real-NVP with MAF in the LSTM-conditioned flow (ablation) | LSTM-Real-NVP · Electricity | CRPS_sum: 0.024 -> 0.0208 | Improved |
| Replace Real-NVP with MAF in the LSTM-conditioned flow (ablation) | LSTM-Real-NVP · Traffic | CRPS_sum: 0.078 -> 0.069 | Improved |
| Replace Real-NVP with MAF in the LSTM-conditioned flow (ablation) | LSTM-Real-NVP · Taxi | CRPS_sum: 0.175 -> 0.161 | Improved |
| Replace Real-NVP with MAF in the LSTM-conditioned flow (ablation) | LSTM-Real-NVP · Wikipedia | CRPS_sum: 0.078 -> 0.067 | Improved |
| Replace Real-NVP with MAF in the LSTM-conditioned flow (ablation) | LSTM-Real-NVP · Exchange | CRPS_sum: 0.0064 -> 0.005 | Improved |
| Use Transformer rather than LSTM for temporal conditioning (ablation) | MAF-conditioned forecasting · Traffic | CRPS_sum: 0.069 -> 0.056 | Improved |
| Use Transformer rather than LSTM for temporal conditioning (ablation) | MAF-conditioned forecasting · Taxi | CRPS_sum: 0.161 -> 0.179 | Hurt |
| Use Transformer rather than LSTM for temporal conditioning (ablation) | MAF-conditioned forecasting · Wikipedia | CRPS_sum: 0.067 -> 0.063 | Improved |
| Use Transformer rather than LSTM for temporal conditioning (ablation) | MAF-conditioned forecasting · Solar | CRPS_sum: 0.315 -> 0.301 | Improved |
| Use Transformer rather than LSTM for temporal conditioning (ablation) | MAF-conditioned forecasting · Electricity | CRPS_sum: 0.0208 -> 0.0207 | No clear effect |
| Use Transformer rather than LSTM for temporal conditioning (ablation) | MAF-conditioned forecasting · Exchange | CRPS_sum: 0.005 -> 0.005 | No clear effect |
Closest papers by meaning
- Probabilistic Forecasting of Irregularly Sampled Time Series with Missing Values via Conditional Normalizing Flows (AAAI 2025 · similarity 0.89)
- SIN: Selective and Interpretable Normalization for Long-Term Time Series Forecasting (ICML 2024 · similarity 0.88)
- Multivariate Probabilistic Time Series Forecasting with Correlated Errors (NeurIPS 2024 · similarity 0.88)
- Latent Diffusion Transformer for Probabilistic Time Series Forecasting (AAAI 2024 · similarity 0.88)
- CATS: Enhancing Multivariate Time Series Forecasting by Constructing Auxiliary Time Series as Exogenous Variables (ICML 2024 · similarity 0.88)
- TimePFN: Effective Multivariate Time Series Forecasting with Synthetic Data (AAAI 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
