LOSCAR-SGD combines local updates, sparse model averaging, and communication-computation overlap with a delay-corrected merge rule, providing convergence rates for smooth non-convex objectives under worker heterogeneity.
Naval Research Logistics Quarterly , volume =
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Ringmaster LMO extends delay-thresholding from ASGD to LMO-based momentum updates, providing convergence guarantees under (L0, L1)-smoothness and time-complexity bounds that recover optimal rates in the Euclidean case.
Extends variable projection to constrained separable nonlinear least-squares via bilevel collapse, yielding exact reduced gradients and a convergent conditional-gradient algorithm.
citing papers explorer
-
Constrained Variable Projection for Structured Problems
Extends variable projection to constrained separable nonlinear least-squares via bilevel collapse, yielding exact reduced gradients and a convergent conditional-gradient algorithm.