SILAGE is a variance-reduced algorithm for nested finite-sum nonconvex optimization that uses O(n) memory, evaluates at most one local group gradient per iteration, and adapts convergence to data heterogeneity parameters δ1 and δ2.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
Formulates a game where competitors in collaborative learning are incentivized to manipulate updates, then proposes mechanisms that restore honest participation for mean estimation, convex SGD, and non-convex federated learning.
citing papers explorer
-
SILAGE: Memory-Efficient, Full-Gradient-Free Nonconvex Optimization for Nested Finite Sums
SILAGE is a variance-reduced algorithm for nested finite-sum nonconvex optimization that uses O(n) memory, evaluates at most one local group gradient per iteration, and adapts convergence to data heterogeneity parameters δ1 and δ2.
-
Incentivizing Honesty among Competitors in Collaborative Learning and Optimization
Formulates a game where competitors in collaborative learning are incentivized to manipulate updates, then proposes mechanisms that restore honest participation for mean estimation, convex SGD, and non-convex federated learning.