Pith. sign in

After a simple derivation, one can have the convergence rate λs = 2ηsL 2−ηsL + 2(1 +ηsL) ( 1− 2ηsL 1 +κ )m

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

Almost Tune-Free Variance Reduction

cs.LG · 2019-08-25 · conditional · novelty 6.0

SVRG and SARAH converge with a weighted averaging scheme driven by estimate sequences, and when combined with Barzilai-Borwein step sizes and an adaptive inner-loop rule they become almost tune-free in numerical tests.

citing papers explorer

Showing 1 of 1 citing paper.

  • Almost Tune-Free Variance Reduction cs.LG · 2019-08-25 · conditional · none · ref 13

    SVRG and SARAH converge with a weighted averaging scheme driven by estimate sequences, and when combined with Barzilai-Borwein step sizes and an adaptive inner-loop rule they become almost tune-free in numerical tests.