pith. sign in

Adaptive subgradient methods for online learning and stochastic optimization,

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

1 Pith paper citing it

fields

cs.LG 1

years

2018 1

verdicts

CONDITIONAL 1

representative citing papers

Federated Learning with Non-IID Data

cs.LG · 2018-06-02 · conditional · novelty 6.0

Non-IID data causes up to 55% accuracy loss in federated learning due to weight divergence measured by earth mover's distance; 5% globally shared data recovers 30% accuracy on CIFAR-10.

citing papers explorer

Showing 1 of 1 citing paper.

  • Federated Learning with Non-IID Data cs.LG · 2018-06-02 · conditional · none · ref 12

    Non-IID data causes up to 55% accuracy loss in federated learning due to weight divergence measured by earth mover's distance; 5% globally shared data recovers 30% accuracy on CIFAR-10.