Research map / Time series / Causal and generative time series
Deep State Space Models for Time Series Forecasting
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| RNN-parameterized linear SSM (DeepState) vs DeepAR with little training data | probabilistic forecasting · electricity, 2-week training range | p50 loss: 0.153 -> 0.087 | Helped |
| DeepState vs DeepAR | probabilistic forecasting · traffic, 3-week training range | p50 loss: 0.126 -> 0.170 | Hurt |
| DeepState vs DeepAR | rolling-day forecasting · electricity | p50/p90 loss: 0.075/0.04 -> 0.083/0.056 | Hurt |
| DeepState vs ets/auto.arima/DeepAR | forecasting · M4-Hourly | p50 loss: 0.052 -> 0.044 | Helped |
| DeepState vs ets | forecasting · tourism-Monthly | p50 loss: 0.093 -> 0.138 | Hurt |
| DeepState vs classical and DeepAR | forecasting · parts | p50/p90 loss: p50 1.273 -> 1.47; p90 1.086 -> 0.935 | Mixed |
| increase examples per group from 20 to 140 (ablation) | DeepState parameter recovery · synthetic day-of-week seasonality | parameter recovery accuracy | Helped |
Closest papers by meaning
- LETS Forecast: Learning Embedology for Time Series Forecasting (ICML 2025 · similarity 0.87)
- Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts (ICLR 2025 · similarity 0.87)
- SynTSBench: Rethinking Temporal Pattern Learning in Deep Learning Models for Time Series (NeurIPS 2025 · similarity 0.87)
- Time-LLM: Time Series Forecasting by Reprogramming Large Language Models (ICLR 2024 · similarity 0.87)
- ProbTS: Benchmarking Point and Distributional Forecasting across Diverse Prediction Horizons (NeurIPS 2024 · similarity 0.87)
- $S^2$IP-LLM: Semantic Space Informed Prompt Learning with LLM for Time Series Forecasting (ICML 2024 · 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.