# Learning with a Drifting Target Concept

arXiv: https://arxiv.org/abs/1505.05215 · HTML: https://mlsanity.com/paper/1505.05215/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 May 2015.

## Built on by (most cited first, 10 of 10)

- [An Adaptive Algorithm for Learning with Unknown Distribution Drift](https://mlsanity.com/paper/2305.02252/) (2023)
- [Model Assessment and Selection under Temporal Distribution Shift](https://mlsanity.com/paper/2402.08672/) (2024)
- [A Stability Principle for Learning under Non-Stationarity](https://mlsanity.com/paper/2310.18304/) (2023)
- [Nonparametric Density Estimation under Distribution Drift](https://mlsanity.com/paper/2302.02460/) (2023)
- [An Improved Algorithm for Learning Drifting Discrete Distributions](https://mlsanity.com/paper/2403.05446/) (2024)
- [Adaptive Estimation and Learning under Temporal Distribution Shift](https://mlsanity.com/paper/2505.15803/) (2025)
- [Finite sample learning of moving targets](https://mlsanity.com/paper/2408.04406/) (2024)
- [On the Change of Decision Boundaries and Loss in Learning with Concept Drift](https://mlsanity.com/paper/2212.01223/) (2022)
- [Distribution-Free Predictive Inference under Unknown Temporal Drift](https://mlsanity.com/paper/2406.06516/) (2024)
- [Efficiently Learning Drifting Halfspaces with Massart Noise](https://mlsanity.com/paper/2606.11149/) (2026)

## Abstract (arXiv)

We study the problem of learning in the presence of a drifting target concept. Specifically, we provide bounds on the error rate at a given time, given a learner with access to a history of independent samples labeled according to a target concept that can change on each round. One of our main contributions is a refinement of the best previous results for polynomial-time algorithms for the space of linear separators under a uniform distribution. We also provide general results for an algorithm capable of adapting to a variable rate of drift of the target concept. Some of the results also describe an active learning variant of this setting, and provide bounds on the number of queries for the labels of points in the sequence sufficient to obtain the stated bounds on the error rates.