# A-Optimal Active Learning

arXiv: https://arxiv.org/abs/2110.09585 · HTML: https://mlsanity.com/paper/2110.09585/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 27 references that are in the map.
- First posted on arXiv 18 Oct 2021.

## Builds on (most cited first, 6 of 6)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Reconciling modern machine learning practice and the bias-variance trade-off](https://mlsanity.com/paper/1812.11118/) (2018)
- [Cost-Effective Active Learning for Deep Image Classification](https://mlsanity.com/paper/1701.03551/) (2017)
- [Large Data and Zero Noise Limits of Graph-Based Semi-Supervised Learning Algorithms](https://mlsanity.com/paper/1805.09450/) (2018)
- [S2: An Efficient Graph Based Active Learning Algorithm with Application to Nonparametric Classification](https://mlsanity.com/paper/1506.08760/) (2015)

## Abstract (arXiv)

In this work we discuss the problem of active learning. We present an approach that is based on A-optimal experimental design of ill-posed problems and show how one can optimally label a data set by partially probing it, and use it to train a deep network. We present two approaches that make different assumptions on the data set. The first is based on a Bayesian interpretation of the semi-supervised learning problem with the graph Laplacian that is used for the prior distribution and the second is based on a frequentist approach, that updates the estimation of the bias term based on the recovery of the labels. We demonstrate that this approach can be highly efficient for estimating labels and training a deep network.