Positively Weighted Kernel Quadrature via Subsampling
arXiv:2107.09597
Abstract
We study kernel quadrature rules with convex weights. Our approach combines the spectral properties of the kernel with recombination results about point measures. This results in effective algorithms that construct convex quadrature rules using only access to i.i.d. samples from the underlying measure and evaluation of the kernel and that result in a small worst-case error. In addition to our theoretical results and the benefits resulting from convex weights, our experiments indicate that this construction can compete with the optimal bounds in well-known examples.
arXiv comment29 pages, NeurIPS 2022 camera-ready version
References in corpus (10)
- Determinantal Processes and Independence
- On the Equivalence between Herding and Conditional Gradient Algorithms
- Large sample analysis of the median heuristic
- Sparse projections onto the simplex
- Frank-Wolfe Bayesian Quadrature: Probabilistic Integration with Theoretical Guarantees
- Optimally-Weighted Herding is Bayesian Quadrature
- Convergence guarantees for kernel-based quadrature rules in misspecified settings
- Random Features for Kernel Approximation: A Survey on Algorithms, Theory, and Beyond
- Nonparametric Heterogeneity Testing For Massive Data
- Estimating the probability that a given vector is in the convex hull of a random sample