activity
20182022
most citedHonest calibration assessment for binary outcome predictions

17 citations · 23 across the 4 of their papers we have counts for

collaborators

7 papers

math.ST2022★ 3 cited

Approximating Symmetrized Estimators of Scatter via Balanced Incomplete U-Statistics

Lutz Duembgen, Klaus Nordhausen

We derive limiting distributions of symmetrized estimators of scatter, where instead of all pairs of the observations we only consider suitably chosen pairs, $1…

stat.ML2022★ 1 cited

Characteristic kernels on Hilbert spaces, Banach spaces, and on sets of measures

Johanna Ziegel, David Ginsbourger, Lutz Dümbgen

We present new classes of positive definite kernels on non-standard spaces that are integrally strictly positive definite or characteristic. In particular, we discuss radial kernel…

math.ST2022★ 17 cited

Honest calibration assessment for binary outcome predictions

Timo Dimitriadis, Lutz Duembgen, Alexander Henzi +2

Probability predictions from binary regressions or machine learning methods ought to be calibrated: If an event is predicted to occur with probability , it should materialize wi…

math.ST2022★ 2 cited

Various New Inequalities for Beta Distributions

Alexander Henzi, Lutz Duembgen

This note provides some new inequalities and approximations for beta distributions, including tail inequalities, exponential inequalities of Hoeffding and Bernstein type, Gaussian…

math.ST2020

Estimation of a Likelihood Ratio Ordered Family of Distributions

Alexandre Mösching, Lutz Duembgen

Consider bivariate observations with unknown conditional distributions of , given that . The goal is…

math.ST2019

Bounding distributional errors via density ratios

Lutz Duembgen, Richard Samworth, Jon Wellner

We present some new and explicit error bounds for the approximation of distributions. The approximation error is quantified by the maximal density ratio of the distribution to…