# Acquisition Conditioned Oracle for Nongreedy Active Feature Acquisition

## TL;DR

This paper introduces the acquisition conditioned oracle (ACO), a nonparametric approach for active feature acquisition that outperforms existing methods by effectively balancing acquisition costs and prediction accuracy.

## Contribution

The paper proposes a novel, nonparametric oracle-based framework for active feature acquisition that overcomes limitations of previous deep learning and greedy approaches.

## Key findings

- ACO outperforms state-of-the-art AFA methods in experiments
- The approach effectively balances cost and accuracy in feature acquisition
- Demonstrates superiority in both predictive and decision-making tasks

## Abstract

We develop novel methodology for active feature acquisition (AFA), the study of how to sequentially acquire a dynamic (on a per instance basis) subset of features that minimizes acquisition costs whilst still yielding accurate predictions. The AFA framework can be useful in a myriad of domains, including health care applications where the cost of acquiring additional features for a patient (in terms of time, money, risk, etc.) can be weighed against the expected improvement to diagnostic performance. Previous approaches for AFA have employed either: deep learning RL techniques, which have difficulty training policies in the AFA MDP due to sparse rewards and a complicated action space; deep learning surrogate generative models, which require modeling complicated multidimensional conditional distributions; or greedy policies, which fail to account for how joint feature acquisitions can be informative together for better predictions. In this work we show that we can bypass many of these challenges with a novel, nonparametric oracle based approach, which we coin the acquisition conditioned oracle (ACO). Extensive experiments show the superiority of the ACO to state-of-the-art AFA methods when acquiring features for both predictions and general decision-making.