Paper-Conference

Scalable Control Variates for Monte Carlo Methods via Stochastic Optimization
Control variates are a well-established tool to reduce the variance of Monte Carlo estimators. However, for large-scale problems …
Cite arXiv
Bayesian Probabilistic Numerical Integration with Tree-Based Models
Bayesian quadrature (BQ) is a method for solving numerical integration problems in a Bayesian manner, which allows users to quantify …
Cite arXiv
Minimum Stein Discrepancy Estimators
When maximum likelihood estimation is infeasible, one often turns to score matching, contrastive divergence, or minimum probability …
Cite arXiv