Low-rank Low Precision Training of Gaussian Processes
From MaRDI portal
Cites work
- "An Adaptive Factorized Nystr\""om Preconditioner for Regularized Kernel Matrices"
- A Modern Analysis of Hutchinson's Trace Estimator
- A unifying view of sparse approximate Gaussian process regression
- Collected matrix derivative results for forward and reverse mode algorithmic differentiation
- Embrace rejection: Kernel matrix approximation by accelerated randomly pivoted Cholesky
- Fast deterministic approximation of symmetric indefinite kernel matrices with high dimensional datasets
- Fast estimation of \(\mathrm{tr}(f(A))\) via stochastic Lanczos quadrature
- Gaussian Processes for Machine Learning
- Hutch++: Optimal Stochastic Trace Estimation
- Improved Variants of the Hutch++ Algorithm for Trace Estimation
- On randomized trace estimates for indefinite matrices with an application to determinants
- Posterior covariance structures in Gaussian processes
- Preconditioned additive Gaussian processes with Fourier acceleration
- Preconditioned Truncated Single-Sample Estimators for Scalable Stochastic Optimization
- Preconditioning for Scalable Gaussian Process Hyperparameter Optimization
- Randomly pivoted Cholesky: practical approximation of a kernel matrix with few entry evaluations
This page was built for publication: Low-rank Low Precision Training of Gaussian Processes
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7424482)