A Unified Theory of Quantum Neural Network Loss Landscapes
Authors: Eric Anschuetz
ICLR 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We here prove that QNNs and their first two derivatives instead generally form what we call Wishart processes, where certain algebraic properties of the network determine the hyperparameters of the process. This Wishart process description allows us to, for the first time: give necessary and sufficient conditions for a QNN architecture to have a Gaussian process limit; calculate the full gradient distribution, generalizing previously known barren plateau results; and calculate the local minima distribution of algebraically constrained QNNs. [...] Formal proofs of the main results are given in Appendix D. |
| Researcher Affiliation | Academia | Eric R. Anschuetz Institute for Quantum Information and Matter & Walter Burke Institute for Theoretical Physics, Caltech Pasadena, CA 91125, USA EMAIL |
| Pseudocode | No | The paper describes mathematical derivations and proofs for a unified theory of quantum neural network loss landscapes, without including any pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide specific repository links, explicit code release statements, or mention code in supplementary materials for the methodology described. |
| Open Datasets | No | The paper discusses theoretical constructs like 'data set comprising multiple input quantum states ρ' but does not refer to any specific publicly available datasets or provide access information for experimental data. |
| Dataset Splits | No | The paper does not mention any specific datasets used for experimentation, thus no dataset split information is provided. |
| Hardware Specification | No | The paper presents a theoretical framework and mathematical proofs, and does not describe any experiments that would require specific hardware specifications. |
| Software Dependencies | No | The paper is theoretical and does not describe any implemented experiments, therefore it does not list specific software dependencies with version numbers. |
| Experiment Setup | No | The paper provides a theoretical analysis of quantum neural network loss landscapes and does not describe an experimental setup with specific hyperparameters or training configurations. |