A finite-time proof shows gradient descent on separable logistic regression reaches a constant-level alignment with the max-margin direction in O(exp(exp(-δ))) iterations, tight up to constants.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Non-asymptotic implicit bias of logistic regression at early-stage gradient descent dynamics
A finite-time proof shows gradient descent on separable logistic regression reaches a constant-level alignment with the max-margin direction in O(exp(exp(-δ))) iterations, tight up to constants.