{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/barren-plateaus-in-quantum-neural-network","title":"Barren plateaus in quantum neural network training landscapes","arxiv_id":"1803.11173","date":"2018-03-29","proceeding":null,"authors":["Jarrod R. McClean","Sergio Boixo","Vadim N. Smelyanskiy","Ryan Babbush","Hartmut Neven"],"abstract":"Many experimental proposals for noisy intermediate scale quantum devices\ninvolve training a parameterized quantum circuit with a classical optimization\nloop. Such hybrid quantum-classical algorithms are popular for applications in\nquantum simulation, optimization, and machine learning. Due to its simplicity\nand hardware efficiency, random circuits are often proposed as initial guesses\nfor exploring the space of quantum states. We show that the exponential\ndimension of Hilbert space and the gradient estimation complexity make this\nchoice unsuitable for hybrid quantum-classical algorithms run on more than a\nfew qubits. Specifically, we show that for a wide class of reasonable\nparameterized quantum circuits, the probability that the gradient along any\nreasonable direction is non-zero to some fixed precision is exponentially small\nas a function of the number of qubits. We argue that this is related to the\n2-design characteristic of random circuits, and that solutions to this problem\nmust be studied.","url_abs":"http://arxiv.org/abs/1803.11173v1","url_pdf":"http://arxiv.org/pdf/1803.11173v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"barren-plateaus-in-quantum-neural-network","repo_url":"https://github.com/XanaduAI/qml/blob/master/implementations/tutorial_barren_plateaus.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.11173","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}