arXiv subjects

Michael Kubal

Publications and source records attributed to Michael Kubal.

3 recordsLinked to original sources

arXiv2026

Benchmarking Quantum and Classical Machine Learning Models on Oncological Data

Machine learning is being increasingly used for the detection, diagnosis, and treatment of cancer. However, models often struggle with biological data due to high dimensionality, limited sample diversity, and complex feature interactions. Recent works have investigated the potential for quantum machine learning models to exhibit improved performance over classical models on this kind of complex data, but have often lacked rigorous empirical evaluation of quantum advantage. In this work, we develop a methodology for fair benchmarking of quantum and classical machine learning models, based on the Red Cedar quantum machine learning and resource estimation framework and AutoML-optimized classical neural networks. We assess the potential for quantum advantage in machine learning across tabular, omics, and spatial oncological datasets drawn from the existing quantum machine learning literature, with a range of preprocessing methods, and find no evidence of quantum advantage. Our results suggest that the field should prioritize analyzing higher-dimensional, more biologically realistic datasets to make meaningful progress toward practical quantum advantage in oncological classification problems.

quant-ph↗

arXiv2025

How many qubits does a machine learning problem require?

For a machine learning paradigm to be generally applicable, it should have the property of universal approximation, that is, it should be able to approximate any target function to any desired degree of accuracy. In variational quantum machine learning, the class of functions that can be learned depend on both the data encoding scheme as well as the architecture of the optimizable part of the model. Here, we show that the property of universal approximation is constructively and efficiently realized by the recently proposed bit-bit data encoding scheme. Further, we show that this construction allows us to calculate the number of qubits required to solve a learning problem on a dataset to a target accuracy, giving rise to the first resource estimation framework for variational quantum machine learning. We apply bit-bit encoding to a number of medium-sized classical benchmark datasets and find that they require only 27 qubits on average for encoding. We extend the basic bit-bit encoding scheme to a variant that efficiently supports batched processing of large datasets. As a demonstration, we apply this new scheme to subsets of a giga-scale transcriptomic dataset. This work establishes bit-bit encoding not only as a universally expressive quantum data representation, but also as a practical foundation for resource estimation and benchmarking in quantum machine learning.

quant-ph↗

arXiv2025

A Quantum Platform for Multiomics Data

The complexity of biological systems, governed by molecular interactions across hierarchical scales, presents a challenge for computational modeling. While advances in multiomic profiling have enabled precise measurements of biological components, classical computational approaches remain limited in capturing emergent dynamics critical for understanding disease mechanisms and therapeutic interventions. Quantum computing offers a new paradigm for addressing classically intractable problems, yet its integration into biological research remains nascent due to scalability barriers and accessibility gaps. Here, we introduce a hybrid quantum-classical machine learning platform designed to bridge this gap, with an encode-search-build approach which allows for efficiently extracting the most relevant information from biological data to \underline{encode} into a quantum state, provably efficient training algorithms to \underline{search} for optimal parameters, and a stacking strategy that allows one to systematically \underline{build} more complex models as more quantum resources become available. We propose to demonstrate the platform's utility through two initial use cases: quantum-enhanced classification of phenotypic states from molecular variables and prediction of temporal evolution in biological systems.

quant-ph↗