Limitations of measure-first protocols in quantum machine learning

Authors: Casper Gyurik, Riccardo Molteni, Vedran Dunjko

ICML 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We prove limitations for the general class of quantum machine learning algorithms that use fixed measurement schemes on the input quantum states. Our main conceptual contribution is to resolve the above question negatively by presenting a concrete machine learning scenario that clearly exhibits the limitations of any measure-first protocol. The precise proofs of Theorem 1.1 can be found in the Appendix.
Researcher Affiliation Collaboration 1applied Quantum algorithms, Leiden University, 2333 CA Leiden, Netherlands 2LIACS, Universiteit Leiden, 2333 CA Leiden, Netherlands 3Pasqal Sa S, 7 rue L eonard de Vinci, 91300 Massy, France. Correspondence to: Casper Gyurik <EMAIL>, Riccardo Molteni <EMAIL>, Vedran Dunjko <EMAIL>.
Pseudocode No The paper describes algorithms and protocols in text, such as the steps for the fully-quantum protocol in Appendix A, but does not use structured pseudocode or algorithm blocks.
Open Source Code No The paper does not contain any statements about releasing source code, nor does it provide links to any code repositories.
Open Datasets No The paper discusses abstract 'quantum states' and 'data' in a theoretical context but does not refer to or provide access information for any empirical, publicly available datasets.
Dataset Splits No The paper does not mention the use of any empirical datasets, and therefore no specific training/test/validation splits are provided.
Hardware Specification No The paper is theoretical and does not describe any experimental hardware used for running simulations or experiments.
Software Dependencies No The paper is theoretical and does not specify any software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not describe any specific experimental setup details or hyperparameters.