Gradient descent on logistic loss for two-layer nonlinear models reduces to perceptron updates, yielding provable Õ(√d) iteration complexity from nonlinearity versus Ω(d) for linear models.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Gradient Descent as a Perceptron Algorithm: Understanding Dynamics and Implicit Acceleration
Gradient descent on logistic loss for two-layer nonlinear models reduces to perceptron updates, yielding provable Õ(√d) iteration complexity from nonlinearity versus Ω(d) for linear models.