The Computational Complexity of Concise Hypersphere Classification
This addresses the difficulty of obtaining interpretable explanations for binary data classification, which is an incremental advance in complexity theory for machine learning.
The paper tackled the computational complexity of finding concise hypersphere classifications for binary data, establishing stronger lower bounds and new fixed-parameter algorithms to enable exact and concise explanations when possible.
Hypersphere classification is a classical and foundational method that can provide easy-to-process explanations for the classification of real-valued and binary data. However, obtaining an (ideally concise) explanation via hypersphere classification is much more difficult when dealing with binary data than real-valued data. In this paper, we perform the first complexity-theoretic study of the hypersphere classification problem for binary data. We use the fine-grained parameterized complexity paradigm to analyze the impact of structural properties that may be present in the input data as well as potential conciseness constraints. Our results include stronger lower bounds and new fixed-parameter algorithms for hypersphere classification of binary data, which can find an exact and concise explanation when one exists.