Monotonicity of aggregated gradients holds if and only if the aggregation rule is positively affine; non-affine rules therefore prevent steady convergence and degrade stability.
arXiv preprint arXiv:2312.14712 , year=
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
-
Dangerous Liaisons of Convex Learning and Non-Affine Aggregation
Monotonicity of aggregated gradients holds if and only if the aggregation rule is positively affine; non-affine rules therefore prevent steady convergence and degrade stability.