# Robust Correction of Sampling Bias Using Cumulative Distribution Functions

arXiv: https://arxiv.org/abs/2010.12687 · HTML: https://mlsanity.com/paper/2010.12687/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Oct 2020.

## Built on by (most cited first, 6 of 6)

- [Double-Weighting for Covariate Shift Adaptation](https://mlsanity.com/paper/2305.08637/) (2023)
- [Inference and Sampling for Archimax Copulas](https://mlsanity.com/paper/2205.14025/) (2022)
- [Efficient CDF Approximations for Normalizing Flows](https://mlsanity.com/paper/2202.11322/) (2022)
- [Classification by estimating the cumulative distribution function for small data](https://mlsanity.com/paper/2210.05953/) (2022)
- [Manually Selecting The Data Function for Supervised Learning of small datasets](https://mlsanity.com/paper/2303.03894/) (2023)
- [Data Augmentation via Causal-Residual Bootstrapping](https://mlsanity.com/paper/2603.15335/) (2026)

## Abstract (arXiv)

Varying domains and biased datasets can lead to differences between the training and the target distributions, known as covariate shift. Current approaches for alleviating this often rely on estimating the ratio of training and target probability density functions. These techniques require parameter tuning and can be unstable across different datasets. We present a new method for handling covariate shift using the empirical cumulative distribution function estimates of the target distribution by a rigorous generalization of a recent idea proposed by Vapnik and Izmailov. Further, we show experimentally that our method is more robust in its predictions, is not reliant on parameter tuning and shows similar classification performance compared to the current state-of-the-art techniques on synthetic and real datasets.