Max-Cost Discrete Function Evaluation Problem under a Budget

TL;DR

This paper introduces new methods for the max-cost Discrete Function Evaluation Problem under budget constraints, focusing on minimizing worst-case costs in applications like clinical diagnosis with provable approximation guarantees.

Contribution

It develops a broad class of admissible impurity functions for flexible, cost-effective decision tree construction with theoretical approximation bounds.

Findings

Proposed admissible impurity functions for flexible cost control.

Achieved $O(\log n)$ approximation guarantees for max-cost minimization.

Enhanced robustness against outliers in cost-sensitive classification.

Abstract

We propose novel methods for max-cost Discrete Function Evaluation Problem (DFEP) under budget constraints. We are motivated by applications such as clinical diagnosis where a patient is subjected to a sequence of (possibly expensive) tests before a decision is made. Our goal is to develop strategies for minimizing max-costs. The problem is known to be NP hard and greedy methods based on specialized impurity functions have been proposed. We develop a broad class of \emph{admissible} impurity functions that admit monomials, classes of polynomials, and hinge-loss functions that allow for flexible impurity design with provably optimal approximation bounds. This flexibility is important for datasets when max-cost can be overly sensitive to "outliers." Outliers bias max-cost to a few examples that require a large number of tests for classification. We design admissible functions that allow for accuracy-cost trade-off and result in $O(\log n)$ guarantees of the optimal cost among trees with corresponding classification accuracy levels.