RA-SQP achieves optimal O(epsilon^-4) gradient and O(epsilon^-2) linear-system complexity for equality-constrained stochastic optimization, and handles general nonlinear constraints via robust subproblems.
Sample size selection in optimization methods for machine learning.Mathematical programming, 134(1):127–155, 2012
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Retrospective Approximation Sequential Quadratic Programming for Stochastic Optimization with General Deterministic Nonlinear Constraints
RA-SQP achieves optimal O(epsilon^-4) gradient and O(epsilon^-2) linear-system complexity for equality-constrained stochastic optimization, and handles general nonlinear constraints via robust subproblems.