The paper defines robustness radius and contamination need for Bayes acts under prior perturbations via linear programming, then builds cost-adjusted selection paths that transition between stability and cost regimes.
Contributions to the decision theoretic foundations of machine learning and robust statistics under weakly structured information
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
This habilitation thesis is cumulative and, therefore, is collecting and connecting research that I (together with several co-authors) have conducted over the last few years. Thus, the absolute core of the work is formed by the ten publications listed on page 5 under the name Contributions 1 to 10. The references to the complete versions of these articles are also found in this list, making them as easily accessible as possible for readers wishing to dive deep into the different research projects. The chapters following this thesis, namely Parts A to C and the concluding remarks, serve to place the articles in a larger scientific context, to (briefly) explain their respective content on a less formal level, and to highlight some interesting perspectives for future research in their respective contexts. Naturally, therefore, the following presentation has neither the level of detail nor the formal rigor that can (hopefully) be found in the papers. The purpose of the following text is to provide the reader an easy and high-level access to this interesting and important research field as a whole, thereby, advertising it to a broader audience.
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
SSLA approximates the posterior predictive distribution by refitting Bayesian models on self-predicted data, yielding a deterministic uncertainty measure that outperforms standard Laplace approximations in calibration on regression tasks.
Using generalized stochastic dominance, the authors find that human-written text completions are not significantly outperformed by five LLM decoding strategies across mixed cardinal and ordinal quality metrics.
citing papers explorer
-
Robust Bayes Acts under Prior Perturbations: Contamination, Stability, and Selection Paths
The paper defines robustness radius and contamination need for Bayes acts under prior perturbations via linear programming, then builds cost-adjusted selection paths that transition between stability and cost regimes.
-
Self-Supervised Laplace Approximation for Bayesian Uncertainty Quantification
SSLA approximates the posterior predictive distribution by refitting Bayesian models on self-predicted data, yielding a deterministic uncertainty measure that outperforms standard Laplace approximations in calibration on regression tasks.
-
Statistical Multicriteria Evaluation of LLM-Generated Text
Using generalized stochastic dominance, the authors find that human-written text completions are not significantly outperformed by five LLM decoding strategies across mixed cardinal and ordinal quality metrics.