Pith. sign in

REVIEW 4 cited by

Additive Powers-of-Two Quantization: An Efficient Non-uniform Discretization for Neural Networks

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1909.13144 v2 pith:KMOMBBKF submitted 2019-09-28 cs.LG stat.ML

Yuhang Li , Xin Dong , Wei Wang This is my paper · ORCID
classification cs.LGstat.ML
keywords quantizationapotdistributionpowers-of-twoweightsadditiveclippingcomputational
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We propose Additive Powers-of-Two~(APoT) quantization, an efficient non-uniform quantization scheme for the bell-shaped and long-tailed distribution of weights and activations in neural networks. By constraining all quantization levels as the sum of Powers-of-Two terms, APoT quantization enjoys high computational efficiency and a good match with the distribution of weights. A simple reparameterization of the clipping function is applied to generate a better-defined gradient for learning the clipping threshold. Moreover, weight normalization is presented to refine the distribution of weights to make the training more stable and consistent. Experimental results show that our proposed method outperforms state-of-the-art methods, and is even competitive with the full-precision models, demonstrating the effectiveness of our proposed APoT quantization. For example, our 4-bit quantized ResNet-50 on ImageNet achieves 76.6% top-1 accuracy without bells and whistles; meanwhile, our model reduces 22% computational cost compared with the uniformly quantized counterpart. The code is available at https://github.com/yhhhli/APoT_Quantization.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. DSTAR: Accelerating Diffusion Transformers via Spatial and Temporal Redundancy Reduction

    cs.AR 2026-07 conditional novelty 6.0 of 10

    DSTAR reports 7.33x latency speedup and 41.89x energy savings over an A100 GPU on seven diffusion transformers by quantizing differential activations to as few as 2 bits and reusing block-wise sparse attention scores.

  2. GRAU: Generic Reconfigurable Activation Unit Design for Neural Network Hardware Accelerators

    cs.AR 2026-02 conditional novelty 6.0 of 10

    GRAU implements reconfigurable QNN activation hardware using power-of-two-slope piecewise linear fits, cutting LUTs by >90% versus multi-threshold units while keeping accuracy within ~1% except for SiLU under aggressi...

  3. Integrating Pruning with Quantization for Efficient Deep Neural Networks Compression

    cs.NE 2025-09 conditional novelty 4.0 of 10

    Simultaneous or sequential integration of geometric-median filter pruning with 4-bit additive-power-of-two quantization compresses ResNet and VGG models on CIFAR-10 by about 15x with modest accuracy loss.

  4. Progressive Element-wise Gradient Estimation for Neural Network Quantization

    cs.LG 2025-08 conditional novelty 4.0 of 10

    PEGE replaces the straight-through estimator with a curriculum-driven blend of quantized and full-precision weights plus an additive discretization-error correction, reporting small accuracy gains on low-bit CNNs.

Pith tools