# Beyond Disagreement-based Agnostic Active Learning

arXiv: https://arxiv.org/abs/1407.2657 · HTML: https://mlsanity.com/paper/1407.2657/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jul 2014.

## Built on by (most cited first, 22 of 22)

- [Machine Learning with a Reject Option: A survey](https://mlsanity.com/paper/2107.11277/) (2021)
- [Active Fairness Auditing](https://mlsanity.com/paper/2206.08450/) (2022)
- [Exponential Savings in Agnostic Active Learning through Abstention](https://mlsanity.com/paper/2102.00451/) (2021)
- [Efficient Active Learning with Abstention](https://mlsanity.com/paper/2204.00043/) (2022)
- [Improved Algorithms for Efficient Active Learning Halfspaces with Massart and Tsybakov noise](https://mlsanity.com/paper/2102.05312/) (2021)
- [Improved Algorithms for Agnostic Pool-based Active Classification](https://mlsanity.com/paper/2105.06499/) (2021)
- [Active Learning in Bayesian Neural Networks with Balanced Entropy Learning Principle](https://mlsanity.com/paper/2105.14559/) (2021)
- [Agnostic Multi-Group Active Learning](https://mlsanity.com/paper/2306.01922/) (2023)
- [Data-Efficient Learning via Minimizing Hyperspherical Energy](https://mlsanity.com/paper/2206.15204/) (2022)
- [Contextual Active Model Selection](https://mlsanity.com/paper/2207.06030/) (2022)
- [Corruption Robust Active Learning](https://mlsanity.com/paper/2106.11220/) (2021)
- [Active Learning Polynomial Threshold Functions](https://mlsanity.com/paper/2201.09433/) (2022)
- [Towards Multimodal Active Learning: Efficient Learning with Limited Paired Data](https://mlsanity.com/paper/2510.03247/) (2025)
- [Error rate control for classification rules in multiclass mixture models](https://mlsanity.com/paper/2109.14235/) (2021)
- [Black-box Generalization of Machine Teaching](https://mlsanity.com/paper/2206.15205/) (2022)
- [A Two-Stage Active Learning Algorithm for k-Nearest Neighbors](https://mlsanity.com/paper/2211.10773/) (2022)
- [Efficient Active Learning Halfspaces with Tsybakov Noise: A Non-convex Optimization Approach](https://mlsanity.com/paper/2310.15411/) (2023)
- [Towards Fundamental Limits for Active Multi-distribution Learning](https://mlsanity.com/paper/2506.17607/) (2025)
- [Active Learning for Contextual Search with Binary Feedbacks](https://mlsanity.com/paper/2110.01072/) (2021)
- [Pool-based Active Learning as Noisy Lossy Compression: Characterizing Label Complexity via Finite Blocklength Analysis](https://mlsanity.com/paper/2602.05333/) (2026)
- [Active Learning with Foundation Model Priors: Efficient Learning under Class Imbalance](https://mlsanity.com/paper/2606.07630/) (2026)
- [Information Design Against Gaming and Learning Adversaries](https://mlsanity.com/paper/2609.31643/) (2026)

## Abstract (arXiv)

We study agnostic active learning, where the goal is to learn a classifier in a pre-specified hypothesis class interactively with as few label queries as possible, while making no assumptions on the true function generating the labels. The main algorithms for this problem are emdisagreement-based active learning, which has a high label requirement, and emmargin-based active learning, which only applies to fairly restricted settings. A major challenge is to find an algorithm which achieves better label complexity, is consistent in an agnostic setting, and applies to general classification problems. In this paper, we provide such an algorithm. Our solution is based on two novel contributions -- a reduction from consistent active learning to confidence-rated prediction with guaranteed error, and a novel confidence-rated predictor.