Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Projected Stein Variational Newton: A Fast and Scalable Bayesian Inference Method in High Dimensions
Peng Chen, Keyi Wu, Joshua Chen, Tom O'Leary-Roseberry, Omar Ghattas
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 |
|---|---|---|---|
| project into Hessian-based low-dimensional subspace and run SVN there (pSVN vs SVN) | SVN · Linear inference, d=16 to 1024 | RMSE of variance | Improved |
| use pSVN instead of SVGD | SVGD · Linear inference, d=256 | RMSE of variance | Improved |
| use pSVN instead of SVN | SVN · Nonlinear inference, d=1089 | RMSE of mean and variance | Improved |
| increase number of samples from 32 to 512 | pSVN · Linear inference, d=256 | RMSE of variance | Improved |
| increase nominal parameter dimension from 289 to over 16K | pSVN · Nonlinear inference | subspace dimension r / convergence | No clear effect |
| increase number of processor cores | pSVN parallel implementation · Nonlinear inference, 256 samples | wall clock time | Improved |
Closest papers by meaning
- Projected Stein Variational Gradient Descent (NeurIPS 2020 · similarity 0.92)
- Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm (NeurIPS 2016 · similarity 0.89)
- Variance Reduction and Quasi-Newton for Particle-Based Variational Inference (ICML 2020 · similarity 0.89)
- On the geometry of Stein variational gradient descent (JMLR 2023 · similarity 0.89)
- ELBOing Stein: Variational Bayes with Stein Mixture Inference (ICLR 2025 · similarity 0.87)
- Training Bayesian Neural Networks with Sparse Subspace Variational Inference (ICLR 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.
