Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Scalable Gaussian Process Separation for Kernels with a Non-Stationary Phase
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 batch GP with warpSKI (multiple non-equidistant inducing point sets) for fetal ECG source separation | fetal ECG source separation · Fetal ECG (n=5000) | inference time and SNR improvement: inference 2.60 s to 0.27 s; SNR 18.6 dB to 18.1 dB | Mixed |
| Scale warpSKI to 10^5 input points for fetal ECG separation | warpSKI · Fetal ECG (n=10^5) | SNR improvement: 18.2 dB, close to batch GP at n=5000 | No clear effect |
| Replace batch GP with warpSKI for fetal ECG hyperparameter learning | fetal ECG model learning · Fetal ECG (n=5000) | learning time: 28.5 s to 47.4 s | Hurt |
| Use warpSKI with non-stationary phase kernel on EIT data (699,825 points) | warpSKI · EIT | nRMSE: 0.176 (EIT) vs 0.217 (BSP) | No clear effect |
Closest papers by meaning
- Non-Stationary Spectral Kernels (NeurIPS 2017 · similarity 0.89)
- Revisiting Nonstationary Kernel Design for Multi-Output Gaussian Processes (ICLR 2026 · similarity 0.89)
- Scalable Gaussian Processes with Latent Kronecker Structure (ICML 2025 · similarity 0.88)
- Exact Gaussian Processes on a Million Data Points (NeurIPS 2019 · similarity 0.88)
- Implicit Gaussian process representation of vector fields over arbitrary latent manifolds (ICLR 2024 · similarity 0.88)
- The Price of Linear Time: Error Analysis of Structured Kernel Interpolation (ICML 2025 · 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.