# Active Information Acquisition

arXiv: https://arxiv.org/abs/1602.02181 · HTML: https://mlsanity.com/paper/1602.02181/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Feb 2016.

## Built on by (most cited first, 11 of 11)

- [Learning to Maximize Mutual Information for Dynamic Feature Selection](https://mlsanity.com/paper/2301.00557/) (2023)
- [Estimating Conditional Mutual Information for Dynamic Feature Selection](https://mlsanity.com/paper/2306.03301/) (2023)
- [Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attribution](https://mlsanity.com/paper/2401.15866/) (2024)
- [Acquisition Conditioned Oracle for Nongreedy Active Feature Acquisition](https://mlsanity.com/paper/2302.13960/) (2023)
- [A Survey on Active Feature Acquisition Strategies](https://mlsanity.com/paper/2502.11067/) (2025)
- [Graph Neural Networks for Multi-Robot Active Information Acquisition](https://mlsanity.com/paper/2209.12091/) (2022)
- [Stochastic Encodings for Active Feature Acquisition](https://mlsanity.com/paper/2508.01957/) (2025)
- [Towards Robust Active Feature Acquisition](https://mlsanity.com/paper/2107.04163/) (2021)
- [Distribution Guided Active Feature Acquisition](https://mlsanity.com/paper/2410.03915/) (2024)
- [Towards Cost Sensitive Decision Making](https://mlsanity.com/paper/2410.03892/) (2024)
- [Uncertainty as a Planning Signal: Multi-Turn Decision Making for Goal-Oriented Conversation](https://mlsanity.com/paper/2604.03924/) (2026)

## Abstract (arXiv)

We propose a general framework for sequential and dynamic acquisition of useful information in order to solve a particular task. While our goal could in principle be tackled by general reinforcement learning, our particular setting is constrained enough to allow more efficient algorithms. In this paper, we work under the Learning to Search framework and show how to formulate the goal of finding a dynamic information acquisition policy in that framework. We apply our formulation on two tasks, sentiment analysis and image recognition, and show that the learned policies exhibit good statistical performance. As an emergent byproduct, the learned policies show a tendency to focus on the most prominent parts of each instance and give harder instances more attention without explicitly being trained to do so.