# Conjunction Subspaces Test for Conformal and Selective Classification

arXiv: https://arxiv.org/abs/2410.12297 · HTML: https://mlsanity.com/paper/2410.12297/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 44 references that are in the map.
- First posted on arXiv 16 Oct 2024.

## Builds on (most cited first, 9 of 9)

- [Distribution-Free, Risk-Controlling Prediction Sets](https://mlsanity.com/paper/2101.02703/) (2021)
- [Machine Learning with a Reject Option: A survey](https://mlsanity.com/paper/2107.11277/) (2021)
- [Prediction and outlier detection in classification problems](https://mlsanity.com/paper/1905.04396/) (2019)
- [Random-projection ensemble classification](https://mlsanity.com/paper/1504.04595/) (2015)
- [Set-valued classification -- overview via a unified framework](https://mlsanity.com/paper/2102.12318/) (2021)
- [On Reject and Refine Options in Multicategory Classification](https://mlsanity.com/paper/1701.02265/) (2017)
- [RaSE: Random Subspace Ensemble Classification](https://mlsanity.com/paper/2006.08855/) (2020)
- [Optimizing model-agnostic Random Subspace ensembles](https://mlsanity.com/paper/2109.03099/) (2021)
- [Instance-Based Classification through Hypothesis Testing](https://mlsanity.com/paper/1901.00560/) (2019)

## Abstract (arXiv)

In this paper, we present a new classifier, which integrates significance testing results over different random subspaces to yield consensus p-values for quantifying the uncertainty of classification decision. The null hypothesis is that the test sample has no association with the target class on a randomly chosen subspace, and hence the classification problem can be formulated as a problem of testing for the conjunction of hypotheses. The proposed classifier can be easily deployed for the purpose of conformal prediction and selective classification with reject and refine options by simply thresholding the consensus p-values. The theoretical analysis on the generalization error bound of the proposed classifier is provided and empirical studies on real data sets are conducted as well to demonstrate its effectiveness.