Gradient descent on any feedforward network with Lipschitz-smooth, linearly bounded activations drives the minimum squared gradient norm to zero at rate O(1/T^(1/L)) without boundedness or overparameterization assumptions.
Non-Uniform Smoothness for Gradient Descent
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
cs.LG 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Convergence Guarantees of Gradient Descent for Neural Networks via Generalized Lipschitz Smoothness
Gradient descent on any feedforward network with Lipschitz-smooth, linearly bounded activations drives the minimum squared gradient norm to zero at rate O(1/T^(1/L)) without boundedness or overparameterization assumptions.