A new alternating stochastic optimization method for multi-objective problems that lowers computational cost per iteration by block and objective alternation while recovering classical convergence rates under convex, non-convex, and PL conditions.
Miettinen.Nonlinear Multiobjective Optimization, volume 12
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Stochastic block coordinate and function alternation for multi-objective optimization and learning
A new alternating stochastic optimization method for multi-objective problems that lowers computational cost per iteration by block and objective alternation while recovering classical convergence rates under convex, non-convex, and PL conditions.