The paper proposes truncated, model-gradient-generated subspaces for large-scale optimization and gives conditional decrease and convergence theorems, but the stated guarantees are not fully proven.
Stochastic first- and zeroth-order methods for non- convex stochastic programming.SIAM J
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
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Model-Driven Subspaces for Large-Scale Optimization with Local Approximation Strategy
The paper proposes truncated, model-gradient-generated subspaces for large-scale optimization and gives conditional decrease and convergence theorems, but the stated guarantees are not fully proven.