Pith. sign in

On large-batch training for deep learning: Generalization gap and sharp minima

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

1 Pith paper citing it

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Explaining How Quantization Disparately Skews a Model

cs.LG · 2025-09-08 · conditional · novelty 4.0

Quantization exacerbates accuracy disparity across groups via a cascade of weight, logit, and probability changes, and a combination of sampling, weighted loss, and mixed-precision training mitigates it.

citing papers explorer

Showing 1 of 1 citing paper.

  • Explaining How Quantization Disparately Skews a Model cs.LG · 2025-09-08 · conditional · none · ref 6

    Quantization exacerbates accuracy disparity across groups via a cascade of weight, logit, and probability changes, and a combination of sampling, weighted loss, and mixed-precision training mitigates it.