Research map / Time series / Causal and generative time series
Markovian Gaussian Process Variational Autoencoders
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 |
|---|---|---|---|
| Replace discrete-time RNN latent dynamics with Markovian GP prior (MGPVAE) inference via Kalman filtering/smoothing | MGPVAE · Rotating MNIST corrupt frames | NLL and RMSE | Helped |
| Replace discrete-time RNN latent dynamics with Markovian GP prior (MGPVAE) | MGPVAE · Rotating MNIST missing frames | NLL and RMSE | Helped |
| Use MGPVAE instead of sparse GPVAE (SVGPVAE) with inducing points | MGPVAE · Spatiotemporal climate data | predictive performance and speed | Helped |
| Use MGPVAE instead of neuralODE / latentODE on Mujoco | MGPVAE · Mujoco action data | NLL and RMSE | Helped |
| Increase SVGPVAE inducing points from 20 to 40 on Mujoco T=1000 (ablation) | SVGPVAE · Mujoco action data T=1000 | NLL/RMSE and memory | Mixed |
Closest papers by meaning
- Gaussian Process Prior Variational Autoencoders (NeurIPS 2018 · similarity 0.91)
- Neighbour-Driven Gaussian Process Variational Autoencoders for Scalable Structured Latent Modelling (ICML 2025 · similarity 0.89)
- Bayesian Basis Function Approximation for Scalable Gaussian Process Priors in Deep Generative Models (ICML 2025 · similarity 0.89)
- Spatio-Temporal Variational Gaussian Processes (NeurIPS 2021 · similarity 0.88)
- eXponential FAmily Dynamical Systems (XFADS): Large-scale nonlinear Gaussian state-space modeling (NeurIPS 2024 · similarity 0.85)
- Recurrent Memory for Online Interdomain Gaussian Processes (NeurIPS 2025 · similarity 0.85)
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.