Research map / Probabilistic and scientific modeling / Dynamical systems
Overcoming Mean-Field Approximations in Recurrent Gaussian Process 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 |
|---|---|---|---|
| Couple latent trajectories and transition function using VCDT instead of the factorised non-linear posterior | GPSSM · Actuator | NLPP: -0.641 -> -0.644 | Helped |
| Couple latent trajectories and transition function using VCDT instead of the factorised non-linear posterior | GPSSM · Ballbeam | NLPP: -1.379 -> -1.395 | Helped |
| Couple latent trajectories and transition function using VCDT instead of the factorised non-linear posterior | GPSSM · Drive | NLPP: 0.283 -> 0.238 | Hurt |
| Couple latent trajectories and transition function using VCDT instead of the factorised non-linear posterior | GPSSM · Dryer | NLPP: -1.310 -> -1.282 | Hurt |
| Couple latent trajectories and transition function using VCDT instead of the factorised non-linear posterior | GPSSM · Gas Furnace | NLPP: 0.264 -> 0.377 | Hurt |
| Replace the factorised non-linear posterior with VCDT | GPSSM · Cart and Pole | NLPP: 1.847 -> 0.694 | Helped |
| Replace the factorised linear posterior with VCDT | GPSSM · Cart and Pole | NLPP: 2.268 -> 0.694 | Helped |
| Use PR-SSM rather than VCDT | GPSSM · Cart and Pole | NLPP: 0.694 -> -0.049 | Helped |
| Add dependence between latent states and the transition function (ablation) | Factorised non-linear GPSSM · Kink function | posterior calibration | Helped |
| Use PR-SSM's prior-transition posterior in a setting with process noise (ablation) | GPSSM · Kink function | predictive performance | Hurt |
Closest papers by meaning
- Variational Inference for Continuous-Time Switching Dynamical Systems (NeurIPS 2021 · similarity 0.91)
- Exact Inference for Continuous-Time Gaussian Process Dynamics (AAAI 2024 · similarity 0.89)
- Variational Inference for SDEs Driven by Fractional Noise (ICLR 2024 · similarity 0.88)
- Amortized Structured Stochastic Variational Inference for Gaussian Process Latent Variable Models (NeurIPS 2026 · similarity 0.87)
- eXponential FAmily Dynamical Systems (XFADS): Large-scale nonlinear Gaussian state-space modeling (NeurIPS 2024 · similarity 0.87)
- Conditioning Gaussian Processes on Almost Anything (NeurIPS 2026 · 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.