Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
A Distributed Variational Inference Framework for Unifying Parallel Sparse Gaussian Process Regression 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 |
|---|---|---|---|
| Replace independent constant noise (DTC) with Markov order B=1 correlated noise (LMA-style) in distributed variational framework | distributed variational SGPR · AIMPEAK | RMSE (km/h): dDTC 10.70 vs dLMA 3.54 | Helped |
| Use Markov order B=0 correlated noise (PIC-style) instead of independent noise (DTC) | distributed variational SGPR · AIRLINE 2M/100K | RMSE (min.): dDTC 36.84 vs dPIC 17.88 | Helped |
| Distributed dLMA vs prior state-of-the-art distributed methods | distributed variational SGPR · AIRLINE 700K/100K | RMSE (min.): 16.50 vs 27.10 (rBCM) | Helped |
| Distributed computation on 16 cores vs centralized | dPIC, dLMA, dDTC · AIMPEAK | training time (sec): dPIC 116 vs PIC 836 s; dLMA 193 vs LMA 1266 s; dDTC 97 vs DTC 537 s | Helped |
| Distributed computation on 32 cores vs centralized | dPIC, dLMA, dDTC · AIRLINE | training time speedup: speedups 12.69 to 13.58 | Helped |
| dDTC has lower per-iteration cost than dPIC/dLMA but much worse RMSE | distributed variational SGPR · AIRLINE | training time vs RMSE trade-off | Mixed |
Closest papers by meaning
- Variational Inference for Gaussian Process Models with Linear Complexity (NeurIPS 2017 · similarity 0.92)
- Asynchronous Distributed Variational Gaussian Process for Regression (ICML 2017 · similarity 0.91)
- Scalable Variational Bayesian Kernel Selection for Sparse Gaussian Process Regression (AAAI 2020 · similarity 0.91)
- Sparse Variational Student-t Processes (AAAI 2024 · similarity 0.89)
- Amortized Structured Stochastic Variational Inference for Gaussian Process Latent Variable Models (NeurIPS 2026 · similarity 0.88)
- New Bounds for Sparse Variational Gaussian Processes (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.