End-to-End Quantum Vision Transformer: Towards Practical Quantum Speedup in Large-Scale Models (2402.18940v2)
Abstract: The field of quantum deep learning presents significant opportunities for advancing computational capabilities, yet it faces a major obstacle in the form of the "information loss problem" due to the inherent limitations of the necessary quantum tomography in scaling quantum deep neural networks. This paper introduces an end-to-end Quantum Vision Transformer (QViT), which incorporates an innovative quantum residual connection technique, to overcome these challenges and therefore optimize quantum computing processes in deep learning. Our thorough complexity analysis of the QViT reveals a theoretically exponential and empirically polynomial speedup, showcasing the model's efficiency and potential in quantum computing applications. We conducted extensive numerical tests on modern, large-scale transformers and datasets, establishing the QViT as a pioneering advancement in applying quantum deep neural networks in practical scenarios. Our work provides a comprehensive quantum deep learning paradigm, which not only demonstrates the versatility of current quantum linear algebra algorithms but also promises to enhance future research and development in quantum deep learning.
- On quantum backpropagation, information reuse, and cheating measurement collapse. arXiv preprint arXiv:2305.13362, 2023.
- Quantum algorithm for linear differential equations with exponentially improved dependence on precision. Communications in Mathematical Physics, 356:1057–1081, 2017.
- Quantum amplitude amplification and estimation. Contemporary Mathematics, 305:53–74, 2002.
- Variational quantum algorithms. Nature Reviews Physics, 3(9):625–644, 2021.
- Quantum approach to accelerate finite volume method on steady computational fluid dynamics problems. Quantum Information Processing, 21(4):137, 2022.
- Quantum vision transformers. arXiv preprint arXiv:2209.08167, 2022.
- Quantum algorithm for systems of linear equations with exponentially improved dependence on precision. SIAM Journal on Computing, 46(6):1920–1950, 2017.
- Contributors, M. Openmmlab’s pre-training toolbox and benchmark. https://github.com/open-mmlab/mmpretrain, 2023.
- Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pp. 248–255. Ieee, 2009.
- Quantum-inspired support vector machine. IEEE Transactions on Neural Networks and Learning Systems, 33(12):7210–7222, 2021.
- An image is worth 16x16 words: Transformers for image recognition at scale. In International Conference on Learning Representations, 2021.
- Quantum singular value transformation and beyond: exponential improvements for quantum matrix arithmetics. In Proceedings of the 51st Annual ACM SIGACT Symposium on Theory of Computing, pp. 193–204, 2019.
- Quantum random access memory. Physical review letters, 100(16):160501, 2008.
- Quantum linear algebra is all you need for transformer architectures. arXiv preprint arXiv:2402.16714, 2024.
- Quantum algorithm for linear systems of equations. Physical review letters, 103(15):150502, 2009.
- Nonlinear transformations in quantum computation. Physical Review Research, 5(1):013105, 2023.
- Quantum algorithms for deep convolutional neural networks. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net, 2020.
- Learning multiple layers of features from tiny images. 2009.
- Krovi, H. Improved quantum algorithms for linear and nonlinear differential equations. Quantum, 7:913, 2023.
- Quantum algorithm for the nonlinear dimensionality reduction with arbitrary kernel. Quantum Science and Technology, 6(1):014001, 2020.
- Towards provably efficient quantum algorithms for large-scale machine-learning models. Nature Communications, 15(1):434, 2024.
- Efficient quantum algorithm for dissipative nonlinear differential equations. Proc Natl Acad Sci U S A, 118(35), 2021.
- Quantum generative adversarial learning. Physical review letters, 121(4):040502, 2018.
- Decoupled weight decay regularization. In International Conference on Learning Representations, 2019.
- Grand unification of quantum algorithms. PRX Quantum, 2(4):040203, 2021.
- Quantum analog-digital conversion. Physical Review A, 99(1):012301, 2019.
- Quantum computation and quantum information. Cambridge university press, 2010.
- Cats and dogs. In 2012 IEEE conference on computer vision and pattern recognition, pp. 3498–3505. IEEE, 2012.
- Quantum gradient descent and newton’s method for constrained polynomial optimization. New Journal of Physics, 21(7):073023, 2019.
- Faster quantum-inspired algorithms for solving linear systems. ACM Transactions on Quantum Computing, 3(4):1–23, 2022.
- A natural nisq model of quantum self-attention mechanism. arXiv preprint arXiv:2305.15680, 2023.
- Quantum algorithms for systems of linear equations inspired by adiabatic quantum computing. Physical review letters, 122(6):060504, 2019.
- Tang, E. A quantum-inspired classical algorithm for recommendation systems. In Proceedings of the 51st annual ACM SIGACT symposium on theory of computing, pp. 217–228, 2019.
- Tang, E. Quantum principal component analysis only achieves an exponential speedup because of its state preparation assumptions. Physical Review Letters, 127(6):060503, 2021.
- Attention is all you need. Advances in neural information processing systems, 30, 2017.
- The caltech-ucsd birds-200-2011 dataset. 2011.
- Quantum homotopy perturbation method for nonlinear dissipative ordinary differential equations. New Journal of Physics, 23(12):123035, 2021.
- Qksan: A quantum kernel self-attention network. arXiv preprint arXiv:2308.13422, 2023.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.