# On the Change of Decision Boundaries and Loss in Learning with Concept Drift

arXiv: https://arxiv.org/abs/2212.01223 · HTML: https://mlsanity.com/paper/2212.01223/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 20 references that are in the map.
- First posted on arXiv 2 Dec 2022.

## Builds on (most cited first, 5 of 5)

- [Scikit-Multiflow: A Multi-output Streaming Framework](https://mlsanity.com/paper/1807.04662/) (2018)
- [Statistical Learning under Nonstationary Mixing Processes](https://mlsanity.com/paper/1512.08064/) (2015)
- [Learning with a Drifting Target Concept](https://mlsanity.com/paper/1505.05215/) (2015)
- [Suitability of Different Metric Choices for Concept Drift Detection](https://mlsanity.com/paper/2202.09486/) (2022)
- [A probability theoretic approach to drifting data in continuous time domains](https://mlsanity.com/paper/1912.01969/) (2019)

## Abstract (arXiv)

The notion of concept drift refers to the phenomenon that the distribution generating the observed data changes over time. If drift is present, machine learning models may become inaccurate and need adjustment. Many technologies for learning with drift rely on the interleaved test-train error (ITTE) as a quantity which approximates the model generalization error and triggers drift detection and model updates. In this work, we investigate in how far this procedure is mathematically justified. More precisely, we relate a change of the ITTE to the presence of real drift, i.e., a changed posterior, and to a change of the training result under the assumption of optimality. We support our theoretical findings by empirical evidence for several learning algorithms, models, and datasets.