no code implementations • 29 Mar 2024 • Paweł Teisseyre, Konrad Furmańczyk, Jan Mielniczuk
Modeling PU data requires certain assumptions on the labeling mechanism that describes which positive observations are assigned a label.
no code implementations • 27 Dec 2023 • Wojciech Rejchel, Paweł Teisseyre, Jan Mielniczuk
In our approach we investigate minimizer of an empirical counterpart of a joint risk which depends on both posterior probability of inclusion in a positive class as well as on a propensity score.
no code implementations • 4 Dec 2023 • Jan Mielniczuk, Adam Wawrzeńczyk
The opposite case when ERM minimizer designed for the case-control case is applied for single-sample data is also considered and similar conclusions are drawn.
1 code implementation • 5 Jun 2023 • Mateusz Płatek, Jan Mielniczuk
We argue that for analysis of Positive Unlabeled (PU) data under Selected Completely At Random (SCAR) assumption it is fruitful to view the problem as fitting of misspecified model to the data.
no code implementations • 16 Sep 2022 • Konrad Furmańczyk, Jan Mielniczuk, Wojciech Rejchel, Paweł Teisseyre
The significant limitation of almost all existing methods lies in assuming that the propensity score function is constant (SCAR assumption), which is unrealistic in many practical situations.
no code implementations • 5 Jul 2019 • Piotr Pokarowski, Wojciech Rejchel, Agnieszka Soltys, Michal Frej, Jan Mielniczuk
These results confirm that, at least for normal linear models, our algorithm seems to be the benchmark for the theory of model selection as it is constructive, computationally efficient and leads to consistent model selection under weak assumptions.
Model Selection Statistics Theory Methodology Statistics Theory
no code implementations • 10 Jun 2019 • Mariusz Kubkowski, Jan Mielniczuk
We consider selection of random predictors for high-dimensional regression problem with binary response for a general loss function.
no code implementations • 22 Oct 2013 • Piotr Pokarowski, Jan Mielniczuk
For the traditional setting (n >p) we give Sanov-type bounds on the error probabilities of the ordering--selection algorithm.