# PowerEvaluationBALD: Efficient Evaluation-Oriented Deep (Bayesian) Active Learning with Stochastic Acquisition Functions

arXiv: https://arxiv.org/abs/2101.03552 · HTML: https://mlsanity.com/paper/2101.03552/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 5 references that are in the map.
- First posted on arXiv 10 Jan 2021.

## Builds on (most cited first, 2 of 2)

- [BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning](https://mlsanity.com/paper/1906.08158/) (2019)
- [Information Condensing Active Learning](https://mlsanity.com/paper/2002.07916/) (2020)

## Built on by (most cited first, 4 of 4)

- [Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational Data](https://mlsanity.com/paper/2111.02275/) (2021)
- [Investigating Multi-source Active Learning for Natural Language Inference](https://mlsanity.com/paper/2302.06976/) (2023)
- [Learning Objective-Specific Active Learning Strategies with Attentive Neural Processes](https://mlsanity.com/paper/2309.05477/) (2023)
- [Boundary-Centric Clip-Budgeted Active Learning for Temporal Action Segmentation](https://mlsanity.com/paper/2604.15173/) (2026)

## Abstract (arXiv)

We develop BatchEvaluationBALD, a new acquisition function for deep Bayesian active learning, as an expansion of BatchBALD that takes into account an evaluation set of unlabeled data, for example, the pool set. We also develop a variant for the non-Bayesian setting, which we call Evaluation Information Gain. To reduce computational requirements and allow these methods to scale to larger acquisition batch sizes, we introduce stochastic acquisition functions that use importance sampling of tempered acquisition scores. We call this method PowerEvaluationBALD. We show in a few initial experiments that PowerEvaluationBALD works on par with BatchEvaluationBALD, which outperforms BatchBALD on Repeated MNIST (MNISTx2), while massively reducing the computational requirements compared to BatchBALD or BatchEvaluationBALD.