Position: Quantum Deep Learning Still Needs a Quantum Leap

Hans Gundlach, Hrvoje Kukina, Jayson Lynch, Neil Thompson
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:170357-170374, 2026.

Abstract

Quantum computing technology is advancing rapidly. Yet, this position paper argues that even accounting for these trends, a quantum leap would be needed for quantum computers to meaningfully impact deep learning over the coming decade or two. We arrive at this conclusion based on a first-of-its-kind survey of quantum algorithms and how they match potential deep learning applications. This survey reveals three important areas where quantum computing could potentially accelerate deep learning, each of which faces a challenging roadblock to realizing its potential. First, quantum algorithms for matrix multiplication and other algorithms central to deep learning offer small theoretical improvements in the number of operations needed, but this advantage is overwhelmed on practical problem sizes by how slowly quantum computers do each operation. Second, some promising quantum algorithms depend on practical Quantum Random Access Memory (QRAM), which is underdeveloped. Finally, there are quantum algorithms that offer large theoretical advantages, but which are only applicable to special cases, limiting their practical benefits. In each of these areas, we support our arguments using quantitative forecasts of quantum advantage for current quantum algorithms that build on the work by Choi et al. (2023) as well as new research on limitations and quantum hardware trends. Our analysis outlines the current scope of quantum deep learning and points to research directions that could lead to greater practical advances in the field.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-gundlach26a, title = {Position: Quantum Deep Learning Still Needs a Quantum Leap}, author = {Gundlach, Hans and Kukina, Hrvoje and Lynch, Jayson and Thompson, Neil}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {170357--170374}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/gundlach26a/gundlach26a.pdf}, url = {https://proceedings.mlr.press/v306/gundlach26a.html}, abstract = {Quantum computing technology is advancing rapidly. Yet, this position paper argues that even accounting for these trends, a quantum leap would be needed for quantum computers to meaningfully impact deep learning over the coming decade or two. We arrive at this conclusion based on a first-of-its-kind survey of quantum algorithms and how they match potential deep learning applications. This survey reveals three important areas where quantum computing could potentially accelerate deep learning, each of which faces a challenging roadblock to realizing its potential. First, quantum algorithms for matrix multiplication and other algorithms central to deep learning offer small theoretical improvements in the number of operations needed, but this advantage is overwhelmed on practical problem sizes by how slowly quantum computers do each operation. Second, some promising quantum algorithms depend on practical Quantum Random Access Memory (QRAM), which is underdeveloped. Finally, there are quantum algorithms that offer large theoretical advantages, but which are only applicable to special cases, limiting their practical benefits. In each of these areas, we support our arguments using quantitative forecasts of quantum advantage for current quantum algorithms that build on the work by Choi et al. (2023) as well as new research on limitations and quantum hardware trends. Our analysis outlines the current scope of quantum deep learning and points to research directions that could lead to greater practical advances in the field.} }
Endnote
%0 Conference Paper %T Position: Quantum Deep Learning Still Needs a Quantum Leap %A Hans Gundlach %A Hrvoje Kukina %A Jayson Lynch %A Neil Thompson %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-gundlach26a %I PMLR %P 170357--170374 %U https://proceedings.mlr.press/v306/gundlach26a.html %V 306 %X Quantum computing technology is advancing rapidly. Yet, this position paper argues that even accounting for these trends, a quantum leap would be needed for quantum computers to meaningfully impact deep learning over the coming decade or two. We arrive at this conclusion based on a first-of-its-kind survey of quantum algorithms and how they match potential deep learning applications. This survey reveals three important areas where quantum computing could potentially accelerate deep learning, each of which faces a challenging roadblock to realizing its potential. First, quantum algorithms for matrix multiplication and other algorithms central to deep learning offer small theoretical improvements in the number of operations needed, but this advantage is overwhelmed on practical problem sizes by how slowly quantum computers do each operation. Second, some promising quantum algorithms depend on practical Quantum Random Access Memory (QRAM), which is underdeveloped. Finally, there are quantum algorithms that offer large theoretical advantages, but which are only applicable to special cases, limiting their practical benefits. In each of these areas, we support our arguments using quantitative forecasts of quantum advantage for current quantum algorithms that build on the work by Choi et al. (2023) as well as new research on limitations and quantum hardware trends. Our analysis outlines the current scope of quantum deep learning and points to research directions that could lead to greater practical advances in the field.
APA
Gundlach, H., Kukina, H., Lynch, J. & Thompson, N.. (2026). Position: Quantum Deep Learning Still Needs a Quantum Leap. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:170357-170374 Available from https://proceedings.mlr.press/v306/gundlach26a.html.

Related Material