Inexact proximal point methods, with Gibbs-sampling or tensor-train estimates of the proximal operator, converge to the global minimum of nonconvex black-box functions under a gap assumption.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Inexact Proximal Point Algorithms for Zeroth-Order Global Optimization
Inexact proximal point methods, with Gibbs-sampling or tensor-train estimates of the proximal operator, converge to the global minimum of nonconvex black-box functions under a gap assumption.