Distribution-free minimization of a convex loss is possible exactly when the loss is uniformly Lipschitz on compact subsets, plus a boundedness condition when the parameter space is unbounded.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.ST 1years
2025 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Distribution free M-estimation
Distribution-free minimization of a convex loss is possible exactly when the loss is uniformly Lipschitz on compact subsets, plus a boundedness condition when the parameter space is unbounded.