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 single-loop stochastic feasible interior-point algorithm for nonlinear inequality-constrained optimization: F
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
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.