On the Impact of Weight Discretization in QUBO-Based SVM Training

TL;DR

This paper investigates how the discretization level of weights in QUBO formulations affects SVM training performance, revealing that low-precision encodings can be competitive and that support vector selection may be more critical than weight precision.

Contribution

It provides an analysis of weight discretization effects in QUBO-based SVM training and compares quantum annealing methods to classical solvers, highlighting the potential and limitations of current hardware.

Findings

Low-precision QUBO encodings can achieve competitive accuracy.

Increasing bit-depth does not always improve classification performance.

Support vector selection may be more important than weight precision.

Abstract

Training Support Vector Machines (SVMs) can be formulated as a QUBO problem, enabling the use of quantum annealing for model optimization. In this work, we study how the number of qubits - linked to the discretization level of dual weights - affects predictive performance across datasets. We compare QUBO-based SVM training to the classical LIBSVM solver and find that even low-precision QUBO encodings (e.g., 1 bit per parameter) yield competitive, and sometimes superior, accuracy. While increased bit-depth enables larger regularization parameters, it does not always improve classification. Our findings suggest that selecting the right support vectors may matter more than their precise weighting. Although current hardware limits the size of solvable QUBOs, our results highlight the potential of quantum annealing for efficient SVM training as quantum devices scale.