# Speeding Up BatchBALD: A k-BALD Family of Approximations for Active Learning

arXiv: https://arxiv.org/abs/2301.09490 · HTML: https://mlsanity.com/paper/2301.09490/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 9 references that are in the map.
- First posted on arXiv 23 Jan 2023.

## Builds on (most cited first, 4 of 4)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning](https://mlsanity.com/paper/1906.08158/) (2019)
- [Stochastic Batch Acquisition: A Simple Baseline for Deep Active Learning](https://mlsanity.com/paper/2106.12059/) (2021)
- [Scalable Batch Acquisition for Deep Bayesian Active Learning](https://mlsanity.com/paper/2301.05490/) (2023)

## Built on by (most cited first, 2 of 2)

- [Making Better Use of Unlabelled Data in Bayesian Active Learning](https://mlsanity.com/paper/2404.17249/) (2024)
- [ConBatch-BAL: Batch Bayesian Active Learning under Budget Constraints](https://mlsanity.com/paper/2507.04929/) (2025)

## Abstract (arXiv)

Active learning is a powerful method for training machine learning models with limited labeled data. One commonly used technique for active learning is BatchBALD, which uses Bayesian neural networks to find the most informative points to label in a pool set. However, BatchBALD can be very slow to compute, especially for larger datasets. In this paper, we propose a new approximation, k-BALD, which uses k-wise mutual information terms to approximate BatchBALD, making it much less expensive to compute. Results on the MNIST dataset show that k-BALD is significantly faster than BatchBALD while maintaining similar performance. Additionally, we also propose a dynamic approach for choosing k based on the quality of the approximation, making it more efficient for larger datasets.