A certificate-based regret analysis framework for guided-diffusion black-box optimization is introduced, with mass lift as the central quantity explaining convergence from pretrained generators.
Finding the needle in the haystack: Materials discovery and design through computational ab initio high-throughput screening.Computational Materials Science, 163:108– 116
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Regret Analysis of Guided Diffusion for Black-Box Optimization over Structured Inputs
A certificate-based regret analysis framework for guided-diffusion black-box optimization is introduced, with mass lift as the central quantity explaining convergence from pretrained generators.