Pith. sign in

Universal stagewise learning for non-convex problems with convergence on averaged solutions

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2019 1

verdicts

CONDITIONAL 1

representative citing papers

Stochastic AUC Maximization with Deep Neural Networks

cs.LG · 2019-08-28 · conditional · novelty 7.0

Under the Polyak-Lojasiewicz condition, a proximal primal-dual algorithm and an AdaGrad-style variant maximize AUC with deep networks at O~(1/epsilon) sample complexity, with adaptive iteration complexity under slow cumulative gradient growth.

citing papers explorer

Showing 1 of 1 citing paper.

  • Stochastic AUC Maximization with Deep Neural Networks cs.LG · 2019-08-28 · conditional · none · ref 5

    Under the Polyak-Lojasiewicz condition, a proximal primal-dual algorithm and an AdaGrad-style variant maximize AUC with deep networks at O~(1/epsilon) sample complexity, with adaptive iteration complexity under slow cumulative gradient growth.