Showing stat.COShow all
3 papers · 1 filter
stat.CO2025
Convergence of a class of gradient-free optimisation schemes when the objective function is noisy, irregular, or both
Christophe Andrieu, Nicolas Chopin, Ettore Fincato +1
We investigate the convergence properties of a class of iterative algorithms designed to minimize a potentially non-smooth and noisy objective function, which may be algebraically…
stat.CO2025
Gradient-free optimization via integration
Christophe Andrieu, Nicolas Chopin, Ettore Fincato +1
We develop and analyse an approach to optimize functions not assumed to be convex, differentiable or even continuous. The algorithm be…
stat.CO2025
Adaptive stratified Monte Carlo using decision trees
Nicolas Chopin, Hejin Wang, Mathieu Gerber
It has been known for a long time that stratification is one possible strategy to obtain higher convergence rates for the Monte Carlo estimation of integrals over the hyper-cube $[…