# Bayesian Active Learning By Distribution Disagreement

arXiv: https://arxiv.org/abs/2501.01248 · HTML: https://mlsanity.com/paper/2501.01248/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 20 references that are in the map.
- First posted on arXiv 2 Jan 2025.

## Builds on (most cited first, 11 of 11)

- [DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks](https://mlsanity.com/paper/1704.04110/) (2017)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Masked Autoregressive Flow for Density Estimation](https://mlsanity.com/paper/1705.07057/) (2017)
- [Neural Spline Flows](https://mlsanity.com/paper/1906.04032/) (2019)
- [BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning](https://mlsanity.com/paper/1906.08158/) (2019)
- [Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets](https://mlsanity.com/paper/2202.02794/) (2022)
- [Sequential Graph Convolutional Network for Active Learning](https://mlsanity.com/paper/2006.10219/) (2020)
- [Bayesian Active Learning with Fully Bayesian Gaussian Processes](https://mlsanity.com/paper/2205.10186/) (2022)
- [Navigating the Pitfalls of Active Learning Evaluation: A Systematic Framework for Meaningful Performance Assessment](https://mlsanity.com/paper/2301.10625/) (2023)
- [ActiveGLAE: A Benchmark for Deep Active Learning with Transformers](https://mlsanity.com/paper/2306.10087/) (2023)
- [Normalizing Flow Ensembles for Rich Aleatoric and Epistemic Uncertainty Modeling](https://mlsanity.com/paper/2302.01312/) (2023)

## Abstract (arXiv)

Active Learning (AL) for regression has been systematically under-researched due to the increased difficulty of measuring uncertainty in regression models. Since normalizing flows offer a full predictive distribution instead of a point forecast, they facilitate direct usage of known heuristics for AL like Entropy or Least-Confident sampling. However, we show that most of these heuristics do not work well for normalizing flows in pool-based AL and we need more sophisticated algorithms to distinguish between aleatoric and epistemic uncertainty. In this work we propose BALSA, an adaptation of the BALD algorithm, tailored for regression with normalizing flows. With this work we extend current research on uncertainty quantification with normalizing flows citeberry2023normalizing, berry2023escaping to real world data and pool-based AL with multiple acquisition functions and query sizes. We report SOTA results for BALSA across 4 different datasets and 2 different architectures.