REVIEW 3 cited by
Quantum Generative Training Using R\'enyi Divergences
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
abstract
Quantum neural networks (QNNs) are a framework for creating quantum algorithms that promises to combine the speedups of quantum computation with the widespread successes of machine learning. A major challenge in QNN development is a concentration of measure phenomenon known as a barren plateau that leads to exponentially small gradients for a range of QNNs models. In this work, we examine the assumptions that give rise to barren plateaus and show that an unbounded loss function can circumvent the existing no-go results. We propose a training algorithm that minimizes the maximal R\'enyi divergence of order two and present techniques for gradient computation. We compute the closed form of the gradients for Unitary QNNs and Quantum Boltzmann Machines and provide sufficient conditions for the absence of barren plateaus in these models. We demonstrate our approach in two use cases: thermal state learning and Hamiltonian learning. In our numerical experiments, we observed rapid convergence of our training loss function and frequently archived a $99\%$ average fidelity in fewer than $100$ epochs.
Forward citations
Cited by 3 Pith papers
-
Pitfalls when tackling the exponential concentration of parameterized quantum models
Exponentially concentrated measurement outcomes are statistically indistinguishable from fixed noise after polynomial shots, so classical post-processing cannot fix them, and common proposed remedies do not escape this.
-
A unifying account of warm start guarantees for patches of quantum landscapes
A new theorem shows that a patch of parameter space around any point with non-exponentially small curvature retains polynomially large loss variance, unifying and extending prior warm-start results for variational qua...
-
iHQGAN: A Lightweight Invertible Hybrid Quantum-Classical Generative Adversarial Network for Unsupervised Image-to-Image Translation
iHQGAN is the first quantum generative adversarial network for unsupervised image-to-image translation, using shared inverse quantum circuits and classical helper networks, with experiments on MNIST-derived edge detec...
Discussion (0). Continue with ORCID to comment.