Reproduce “Variational Inference for Quantum HyperNetworks” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Luca Nepote, Alix Lhéritier, Nicolas Bondoux, Marios Kountouris, Maurizio Filippone
The paper extends Quantum HyperNetworks by training a quantum circuit to generate distributions over candidate binary neural networks, then regularizing them. It uses a variational-inference objective when probabilities are accessible and squared-MMD otherwise. On simulated toy tasks, SELBO reaches 0.991 ± 0.011 Gaussian test accuracy versus 0.893 ± 0.108 for circuit MLE, below the 0.993 exhaustive-search result.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.