Research map / Time series / Causal and generative time series
Probabilistic Recurrent State-Space Models
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 |
|---|---|---|---|
| Use PR-SSM instead of SS-GP-SSM | Markovian state-space model learning · Ballbeam test | RMSE: 411.6 (273.0) -> 0.073 (0.007) | Helped |
| Use PR-SSM instead of SS-GP-SSM | Markovian state-space model learning · Drives test | RMSE: 0.718 (0.009) -> 0.492 (0.038) | Helped |
| Use PR-SSM instead of SS-GP-SSM | Markovian state-space model learning · Actuator test | RMSE: 0.696 (0.034) -> 0.502 (0.031) | Helped |
| Use PR-SSM instead of SS-GP-SSM | Markovian state-space model learning · Furnace test | RMSE: 1.318 (0.027) -> 1.249 (0.029) | Helped |
| Use PR-SSM instead of SS-GP-SSM | Markovian state-space model learning · Dryer test | RMSE: 0.152 (0.006) -> 0.140 (0.018) | Helped |
| Use PR-SSM instead of GP-NARX | Sarcos forward dynamics · Sarcos test | RMSE: 0.169 (-) -> 0.049 (-) | Helped |
| Train with stochastic minibatched ELBO gradients and an initial-state recognition model rather than full-trajectory gradients (ablation) | PR-SSM · Drives | RMSE | No clear effect |
| Train with stochastic minibatched ELBO gradients and an initial-state recognition model rather than full-trajectory gradients (ablation) | PR-SSM · Drives | negative log likelihood | Helped |
Closest papers by meaning
- Effectively Modeling Time Series with Simple Discrete State Spaces (ICLR 2023 · similarity 0.90)
- Hidden Parameter Recurrent State Space Models For Changing Dynamics Scenarios (ICLR 2022 · similarity 0.90)
- From Generalization Analysis to Optimization Designs for State Space Models (ICML 2024 · similarity 0.89)
- Probabilistic Transformer For Time Series Analysis (NeurIPS 2021 · similarity 0.89)
- A Generalizable Physics-Enhanced State Space Model for Long-Term Dynamics Forecasting in Complex Environments (ICML 2025 · similarity 0.86)
- Autocorrelation Matters: Understanding the Role of Initialization Schemes for State Space Models (ICLR 2025 · 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.