# A Unified Theory of Quantum Neural Network Loss Landscapes

arXiv: https://arxiv.org/abs/2408.11901 · HTML: https://mlsanity.com/paper/2408.11901/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Aug 2024.

## Built on by (most cited first, 12 of 12)

- [A Primer on Quantum Machine Learning](https://mlsanity.com/paper/2511.15969/) (2025)
- [Layerwise Federated Learning for Heterogeneous Quantum Clients using Quorus](https://mlsanity.com/paper/2510.06228/) (2025)
- [Resource-efficient equivariant quantum convolutional neural networks](https://mlsanity.com/paper/2410.01252/) (2024)
- [Enhancing variational quantum algorithms by balancing training on classical and quantum hardware](https://mlsanity.com/paper/2503.16361/) (2025)
- [A Universal Quantum Computer From Relativistic Motion](https://mlsanity.com/paper/2411.00105/) (2024)
- [Connecting phases of matter to the flatness of the loss landscape in analog variational quantum algorithms](https://mlsanity.com/paper/2506.13865/) (2025)
- [Fragmentation is Efficiently Learnable by Quantum Neural Networks](https://mlsanity.com/paper/2512.00751/) (2025)
- [Cautious optimism for deep parameterized quantum circuits](https://mlsanity.com/paper/2607.21409/) (2026)
- [Dynamical Lie Algebras Cannot Describe Shallow QAOA: Cragged Terrains, Barren Plateaus, and Empirical Hardness Models](https://mlsanity.com/paper/2608.04252/) (2026)
- [Modeling quantum neural network gradient with reinforcement learning](https://mlsanity.com/paper/2609.31066/) (2026)
- [SQUARE: Structured Quantum Representation Adapters as Compact Quadratic Feature Maps for Frozen Language Models](https://mlsanity.com/paper/2609.37134/) (2026)
- [Gaussian Universality and Its Breakdown in Tensor-Network Machine Learning](https://mlsanity.com/paper/2610.06080/) (2026)

## Abstract (arXiv)

Classical neural networks with random initialization famously behave as Gaussian processes in the limit of many neurons, which allows one to completely characterize their training and generalization behavior. No such general understanding exists for quantum neural networks (QNNs), which -- outside of certain special cases -- are known to not behave as Gaussian processes when randomly initialized. 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. Our unified framework suggests a certain simple operational definition for the "trainability" of a given QNN model using a newly introduced, experimentally accessible quantity we call the "degrees of freedom" of the network architecture.