Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference

On the reading lists

• #58 in Deep learning (2026 edition)

Why it matters

Established practical integer-only inference and quantization-aware training for mobile deployment.

Condensed from the expert lists' notes.

The record

First released

2017 (from arXiv 1712.05877)

Published

2018

Citations

4,917 citations, as counted by Papers With Code (CC BY-SA 4.0)

Named by

both expert lists

Score

0.331 · computed rank 526 · consensus 0.37, must-read 0, citations percentile 0.628 (2010s · deep-learning), awards 0, existing lists 0. Method