Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Robust and Scalable Gaussian Process Regression and Its Applications
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 a uniform-outlier and Gaussian-inlier mixture with variational inference | Gaussian process regression · Neal and Friedman datasets | MAE: Neal: 0.03 -> 0.01 (10%); 0.06 -> 0.03 (50%); 0.35 -> 0.03 (80%). Friedman: 0.11 -> 0.04 (20%); 0.13 -> 0.06 (30%); 1.47 | Helped |
| Use robust GPR for correspondence filtering | Feature matching · YFCC100M relative pose estimation | precision: 63.0 -> 85.3 | Helped |
| Use robust GPR for geometric estimation | Feature matching · HPatches homography estimation | accuracy: 77.7 -> 78.1 | Helped |
| Use robust GPR for geometric estimation | Feature matching · CPC fundamental matrix estimation | accuracy: 47.0 -> 49.6 | Helped |
| Use robust GPR for dense expression imputation | Gene expression imputation · Mouse olfactory bulb, Pattern 1 | MAE: 0.07 -> 0.03 | Helped |
| Use robust GPR for dense expression imputation | Gene expression imputation · Breast cancer tissue, Pattern 1 | MAE: 0.19 -> 0.12 | Helped |
| Add stochastic variational inference (ablation) | RS-GPR · YFCC100M feature matching | F1: 70.0 -> 75.6 | Helped |
| Add inducing variables (ablation) | RS-GPR · YFCC100M feature matching | F1: 69.5 -> 75.6 | Helped |
| Use fixed default kernel hyperparameters rather than optimizing them (ablation) | RS-GPR · YFCC100M feature matching | F1: 67.7 -> 75.6 | Helped |
| Use variational inference instead of EM optimization (ablation) | RS-GPR · YFCC100M feature matching | F1: 65.5 -> 75.6 | Helped |
| Include the posterior variance term Aii when estimating inlier probabilities (ablation) | Robust GPR · Neal data | regression fit | Helped |
Closest papers by meaning
- Robust Gaussian Processes via Relevance Pursuit (NeurIPS 2024 · similarity 0.89)
- Sparse Variational Student-t Processes (AAAI 2024 · similarity 0.88)
- Robust and Computation-Aware Gaussian Processes (NeurIPS 2025 · similarity 0.87)
- New Bounds for Sparse Variational Gaussian Processes (ICML 2025 · similarity 0.87)
- Preventing Model Collapse in Gaussian Process Latent Variable Models (ICML 2024 · similarity 0.87)
- Neighbour-Driven Gaussian Process Variational Autoencoders for Scalable Structured Latent Modelling (ICML 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.