Pith. sign in

REVIEW 6 cited by

Mixed Precision DNNs: All you need is a good parametrization

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 1905.11452 v3 pith:X547YFFT submitted 2019-05-27 cs.LG cs.CVstat.ML

Stefan Uhlich , Lukas Mauch , Fabien Cardinaux , Kazuki Yoshiyama , Javier Alonso Garcia , Stephen Tiedemann , Thomas Kemp , Akira Nakamura This is my paper · ORCID
classification cs.LGcs.CVstat.ML
keywords bitwidthmixedparametersperformanceprecisionquantizationquantizerachieve
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Efficient deep neural network (DNN) inference on mobile or embedded devices typically involves quantization of the network parameters and activations. In particular, mixed precision networks achieve better performance than networks with homogeneous bitwidth for the same size constraint. Since choosing the optimal bitwidths is not straight forward, training methods, which can learn them, are desirable. Differentiable quantization with straight-through gradients allows to learn the quantizer's parameters using gradient methods. We show that a suited parametrization of the quantizer is the key to achieve a stable training and a good final performance. Specifically, we propose to parametrize the quantizer with the step size and dynamic range. The bitwidth can then be inferred from them. Other parametrizations, which explicitly use the bitwidth, consistently perform worse. We confirm our findings with experiments on CIFAR-10 and ImageNet and we obtain mixed precision DNNs with learned quantization parameters, achieving state-of-the-art performance.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

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

  1. SQuaT: Self-Supervised Knowledge Distillation via Student-Aware Quantized Teacher Features

    cs.LG 2026-08 conditional novelty 6.0 of 10

    SQuaT projects teacher features onto the student's quantization lattice to eliminate the unattainable-target lower bound in label-free QAT distillation.

  2. Towards Accurate and Efficient Sub-8-Bit Integer Training

    cs.LG 2024-11 conditional novelty 6.0 of 10

    Sub-8-bit integer training can be made accurate and efficient using power-of-two channel grouping (ShiftQuant) and fully quantized L1 normalization, with reported accuracy close to full precision.

  3. APQF: Agentic Profiling-Guided Structured Pruning and Mixed-Precision Quantization with Adaptive Fine-Tuning

    cs.CV 2026-08 conditional novelty 5.0 of 10

    A profiling-guided, LLM-driven framework combines structured pruning and mixed-precision quantization-aware training, reporting 13-18x bit-operation reductions with modest accuracy loss on ImageNet and CIFAR-10.

  4. Harnessing Input-Adaptive Inference for Efficient VLN

    cs.CV 2025-08 conditional novelty 5.0 of 10

    A three-part input-adaptive inference method (view masking, adaptive early exit, view caching) cuts VLN computation roughly in half on seven benchmarks with moderate success-rate loss.

  5. Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning

    cs.CV 2025-05 conditional novelty 5.0 of 10

    A sharpness-aware, gradient-aligned search finds mixed-precision quantization policies on small proxy datasets that transfer to ImageNet with matching accuracy and faster convergence.

  6. A 1Mb mixed-precision quantized encoder for image classification and patch-based compression

    cs.CV 2025-01 conditional novelty 5.0 of 10

    A reconfigurable 1 Mb mixed-precision encoder performs CIFAR-10 classification at 87.5% accuracy and patch-based VGA compression at 0.25 bpp with a full-frame decoder.

Pith tools