Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Scalable Levy Process Priors for Spectral Kernel Learning
Phillip A Jang, Andrew Loeb, Matthew Davidow, Andrew G Wilson
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| Model the spectral density with a Lévy process prior and average predictions across posterior kernels | Airline passenger data · Airline passenger data (first 96 months training, last 48 months testing) | 95% predictive interval coverage | Improved |
| Use RJ-MCMC with the Lévy process prior instead of fixing spectral mixture parameters | Spectral kernel learning · Airline passenger data | predictive uncertainty | Improved |
| Use a broad, simple frequency initialization rather than a carefully fitted initialization | Lévy spectral kernel learning · Ground-truth frequency recovery | frequency recovery | No clear effect |
| Use a Lévy process prior with Laplacian basis functions rather than an RBF kernel | Direct spectrum regression · Noisy test function | spectrum fit | Improved |
| Use a Lévy spectral kernel process with structured kernel interpolation | Lévy spectral kernel learning · 100,000-point natural sound waveform | training scalability | Improved |
| Use a Lévy process prior that induces sparse spectral mixture coefficients | Lévy spectral kernel learning · Noisy test function | false-positive mixture components | Improved |
Closest papers by meaning
- Scalable Log Determinants for Gaussian Process Kernel Learning (NeurIPS 2017 · similarity 0.89)
- Function-Space Distributions over Kernels (NeurIPS 2019 · similarity 0.88)
- Efficient Approximate Inference for Stationary Kernel on Frequency Domain (ICML 2022 · similarity 0.88)
- Solving High Frequency and Multi-Scale PDEs with Gaussian Processes (ICLR 2024 · similarity 0.87)
- On the Consistency of Kernel Methods with Dependent Observations (ICML 2024 · similarity 0.87)
- Generalization in Kernel Regression Under Realistic Assumptions (ICML 2024 · 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.
