Research map / Time series / Causal and generative time series
Parametric Prior Mapping Framework for Non-stationary Probabilistic Time Series Forecasting
Jinglin Li, Jun Tan, QI Fang, Ning Gui
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 |
|---|---|---|---|
| add push-forward mapping to Gaussian prior (ablation) | PPM · ETTm2 | QICE: 2.286 -> 1.580 | Improved |
| add push-forward mapping to Uniform prior (ablation) | PPM · ETTm2 | QICE: 4.280 -> 1.626 | Improved |
| add push-forward mapping to Gaussian prior (ablation) | PPM · Traffic | CRPS: 0.266 -> 0.252 | Improved |
| add push-forward mapping to Gaussian prior (ablation) | PPM · Traffic | QICE: 2.414 -> 2.744 | Hurt |
| add push-forward mapping to Uniform prior (ablation) | PPM · Traffic | QICE: 3.715 -> 2.616 | Improved |
| add push-forward mapping to Gaussian prior (ablation) | PPM · ETTm2 | CRPS: 0.237 -> 0.237 | No clear effect |
| add NLL term to the loss (ablation) | PPM · ETTm1 and Electricity | CRPS and QICE | Improved |
| add MM (mean MSE) term to the loss (ablation) | PPM · ETTm1 and Electricity | MSE | Improved |
| use MLP backbone instead of ns_Transformer | PPM · Traffic | MSE: 0.655 -> 0.524 | Improved |
| wrap iTransformer with PPM | iTransformer · Traffic | MSE: 0.453 -> 0.464 | Hurt |
| wrap MLP with PPM | MLP · Traffic | MSE: 0.610 -> 0.524 | Improved |
| wrap ns_Transformer with PPM | ns_Transformer · Traffic | MSE: 0.633 -> 0.655 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- iTransformer — iTransformer: Inverted Transformers Are Effective for Time Series Forecasting (ICLR 2024) · better on 0 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Probabilistic Forecasting with Stochastic Interpolants and Föllmer Processes (ICML 2024 · similarity 0.88)
- Non-stationary Diffusion For Probabilistic Time Series Forecasting (ICML 2025 · similarity 0.87)
- HDT: Hierarchical Discrete Transformer for Multivariate Time Series Forecasting (AAAI 2025 · similarity 0.87)
- Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting (ICLR 2025 · similarity 0.86)
- Multivariate Probabilistic Time Series Forecasting with Correlated Errors (NeurIPS 2024 · similarity 0.86)
- TimeES: Probabilistic and Deterministic Time Series Forecasting via Evolutionary Spectra (NeurIPS 2026 · similarity 0.86)
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.
