Limits of Quantum Generative Models Explored

This paper investigates the limitations of quantum generative models, particularly focusing on their ability to achieve quantum advantage. It highlights a trade-off: models that exhibit quantum advantage (e.g., those that anticoncentrate) are difficult to train, while models outputting sparse distributions are more trainable but may be susceptible to classical simulation. The work suggests that quantum advantage in generative models must arise from sources other than anticoncentration.

• •Quantum generative models face limitations in trainability.
• •Models exhibiting quantum advantage (anticoncentrating) are hard to train.
• •Sparse distribution models are more trainable but may be classically simulable.
• •Quantum advantage in generative models likely stems from sources other than anticoncentration.