A deterministic sampling method via maximum mean discrepancy flow with adaptive kernel
From MaRDI portal
Cites work
- (De)-regularized maximum mean discrepancy gradient flow
- A comprehensive survey and analysis of generative models in machine learning
- A generalized discrepancy and quadrature error bound
- A kernel two-sample test
- A variational perspective on accelerated methods in optimization
- An introduction to variational methods for graphical models
- Centered L₂-discrepancy of random sampling and Latin hypercube design, and construction of uniform designs
- Energy statistics: a class of statistics based on distances
- Gibbs Flow for Approximate Transport with Applications to Bayesian Computation
- Goodness-of-fit statistics, discrepancies and robust designs
- Information Theory and Statistics: A Tutorial
- Machine learning from a continuous viewpoint. I
- Miscellanea. A connection between uniformity and aberration in regular fractions of two-level factorials
- Monotone Operators and the Proximal Point Algorithm
- On the limited memory BFGS method for large scale optimization
- Particle-based energetic variational inference
- Quasi-Random Sampling for Multivariate Distributions via Generative Neural Networks
- Reciprocal Relations in Irreversible Processes. I.
- Reciprocal Relations in Irreversible Processes. II.
- Sampling can be faster than optimization
- Some general theorems relating to vibrations.
- Support points
- The Bayesian update: variational formulations and gradient flows
- The trio identity for quasi-Monte Carlo error
- The Variational Formulation of the Fokker--Planck Equation
- Uniform Design: Theory and Application
- Uniform designs limit aliasing
- Universal kernels
- Variational inference for latent variables and uncertain inputs in Gaussian processes
This page was built for publication: A deterministic sampling method via maximum mean discrepancy flow with adaptive kernel
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7323869)
