Reproduce “Conservative quantum offline model-based optimization” 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
Kristian Sotirov, Annie E. Paine, Savvas Varsamopoulos, Antonio A. Gentile, Osvaldo Simeone
COM-QEL adapts quantum extremal learning for offline optimization, where new evaluations are unavailable. It trains a parameterized quantum circuit surrogate on observed data and penalizes optimistic predictions on inputs reached by gradient ascent. In three synthetic continuous-function settings, COM-QEL improves usefulness over QEL; on Ackley, it avoids very low usefulness but has lower novelty than QEL and classical COM.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.