A Lie Algebraic Theory of Barren Plateaus for Deep Parameterized Quantum Circuits
Abstract: Variational quantum computing schemes train a loss function by sending an initial state through a parametrized quantum circuit, and measuring the expectation value of some operator. Despite their promise, the trainability of these algorithms is hindered by barren plateaus (BPs) induced by the expressiveness of the circuit, the entanglement of the input data, the locality of the observable, or the presence of noise. Up to this point, these sources of BPs have been regarded as independent. In this work, we present a general Lie algebraic theory that provides an exact expression for the variance of the loss function of sufficiently deep parametrized quantum circuits, even in the presence of certain noise models. Our results allow us to understand under one framework all aforementioned sources of BPs. This theoretical leap resolves a standing conjecture about a connection between loss concentration and the dimension of the Lie algebra of the circuit's generators.
- E. Farhi, J. Goldstone, and S. Gutmann, A quantum approximate optimization algorithm, arXiv preprint arXiv:1411.4028 (2014).
- M. Schuld, I. Sinayskiy, and F. Petruccione, An introduction to quantum machine learning, Contemporary Physics 56, 172 (2015).
- E. R. Anschuetz and B. T. Kiani, Beyond barren plateaus: Quantum variational algorithms are swamped with traps, Nature Communications 13, 7760 (2022).
- L. Bittel and M. Kliesch, Training variational quantum algorithms is NP-hard, Phys. Rev. Lett. 127, 120502 (2021).
- C. O. Marrero, M. Kieferová, and N. Wiebe, Entanglement-induced barren plateaus, PRX Quantum 2, 040316 (2021).
- L. Friedrich and J. Maziero, Quantum neural network cost function concentration dependency on the parametrization expressivity, Scientific Reports 13, 9978 (2023).
- M. Kieferova, O. M. Carlos, and N. Wiebe, Quantum Generative Training Using Rényi Divergences, arXiv preprint arXiv:2106.09567 (2021).
- E. C. Martín, K. Plekhanov, and M. Lubasch, Barren plateaus in quantum tensor network optimization, arXiv preprint arXiv:2209.00292 (2022).
- A. Uvarov and J. D. Biamonte, On barren plateaus and cost function locality in variational quantum algorithms, Journal of Physics A: Mathematical and Theoretical 54, 245301 (2021).
- M. Kashif and S. Al-Kuwari, The impact of cost function globality and locality in hybrid quantum neural networks on nisq devices, Machine Learning: Science and Technology 4, 015004 (2023).
- A. Uvarov, J. D. Biamonte, and D. Yudin, Variational quantum eigensolver for frustrated quantum systems, Physical Review B 102, 075104 (2020).
- R. Shaydulin and S. M. Wild, Importance of kernel bandwidth in quantum machine learning, Physical Review A 106, 042407 (2022).
- D. Stilck França and R. Garcia-Patron, Limitations of optimization algorithms on noisy quantum devices, Nature Physics 17, 1221 (2021).
- D. García-Martín, M. Larocca, and M. Cerezo, Effects of noise on the overparametrization of quantum neural networks, arXiv preprint arXiv:2302.05059 10.48550/arXiv.2302.05059 (2023).
- R. Zeier and T. Schulte-Herbrüggen, Symmetry principles in quantum systems theory, Journal of mathematical physics 52, 113510 (2011).
- D. D’Alessandro, Introduction to Quantum Control and Dynamics, Chapman & Hall/CRC Applied Mathematics & Nonlinear Science (Taylor & Francis, 2007).
- A. W. Knapp, Lie Groups Beyond an Introduction, Vol. 140 (Springer Science & Business Media, 2013).
- B. Collins, S. Matsumoto, and J. Novak, The weingarten calculus, Notices Of The American Mathematical Society 69, 734 (2022).
- S. Kazi, M. Larocca, and M. Cerezo, On the universality of snsubscript𝑠𝑛s_{n}italic_s start_POSTSUBSCRIPT italic_n end_POSTSUBSCRIPT-equivariant k𝑘kitalic_k-body gates, arXiv preprint arXiv:2303.00728 (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.