MIND uses sliced Wasserstein distance on Inception features to evaluate generative models, matching FID performance with 10x fewer samples and 100x faster computation while being more robust to moment-matching attacks.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Improving broken-symmetry trial wavefunctions in phaseless AFQMC for Fe-S clusters can worsen energy accuracy until high fidelity, linked to measurement trial selection and suggesting error cancellation in HF-based results.
citing papers explorer
-
MIND: Monge Inception Distance for Generative Models Evaluation
MIND uses sliced Wasserstein distance on Inception features to evaluate generative models, matching FID performance with 10x fewer samples and 100x faster computation while being more robust to moment-matching attacks.
-
Can phaseless auxiliary-field quantum Monte Carlo with broken symmetry trials describe iron-sulfur clusters?
Improving broken-symmetry trial wavefunctions in phaseless AFQMC for Fe-S clusters can worsen energy accuracy until high fidelity, linked to measurement trial selection and suggesting error cancellation in HF-based results.