SPBM extends classical penalty-barrier methods to stochastic non-convex non-smooth settings via exponential dual averaging and Moreau envelopes, matching baselines with linear overhead up to 10,000 constraints.
Stochastic approximation for expectation objective and expectation inequality-constrained nonconvex optimization
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A noise-tolerant SQP method with relaxations achieves global convergence and solution accuracy proportional to the noise level for inequality-constrained problems.
citing papers explorer
-
Stochastic Penalty-Barrier Methods for Constrained Machine Learning
SPBM extends classical penalty-barrier methods to stochastic non-convex non-smooth settings via exponential dual averaging and Moreau envelopes, matching baselines with linear overhead up to 10,000 constraints.
-
A Noise Tolerant SQP Algorithm for Inequality Constrained Optimization
A noise-tolerant SQP method with relaxations achieves global convergence and solution accuracy proportional to the noise level for inequality-constrained problems.