Pith. sign in

Quantization-Guided Training for Compact TinyML Models

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

1 Pith paper citing it
abstract

We propose a Quantization Guided Training (QGT) method to guide DNN training towards optimized low-bit-precision targets and reach extreme compression levels below 8-bit precision. Unlike standard quantization-aware training (QAT) approaches, QGT uses customized regularization to encourage weight values towards a distribution that maximizes accuracy while reducing quantization errors. One of the main benefits of this approach is the ability to identify compression bottlenecks. We validate QGT using state-of-the-art model architectures on vision datasets. We also demonstrate the effectiveness of QGT with an 81KB tiny model for person detection down to 2-bit precision (representing 17.7x size reduction), while maintaining an accuracy drop of only 3% compared to a floating-point baseline.

citation-role summary

background 1

citation-polarity summary

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

unclear 1

representative citing papers

Quantizing Small-Scale State-Space Models for Edge AI

cs.LG · 2025-06-14 · conditional · novelty 4.0

Quantization-aware training with a frozen state matrix lifts sequential MNIST accuracy from 40% under post-training quantization to 96%, and a heterogeneous precision scheme cuts memory by 6 times.

citing papers explorer

Showing 1 of 1 citing paper.

  • Quantizing Small-Scale State-Space Models for Edge AI cs.LG · 2025-06-14 · conditional · none · ref 13 · internal anchor

    Quantization-aware training with a frozen state matrix lifts sequential MNIST accuracy from 40% under post-training quantization to 96%, and a heterogeneous precision scheme cuts memory by 6 times.