Sobolev-ball constraints on the hypothesis class achieve minimax rates for score estimation on the torus and, under conjecture, for generative modeling.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.ST 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Optimal score function estimation via derivatives constraints
Sobolev-ball constraints on the hypothesis class achieve minimax rates for score estimation on the torus and, under conjecture, for generative modeling.