paper-with-me

Papers

Bridging the Accuracy Gap for 2-bit Quantized Neural Networks (QNN)

2018-07-17 · Jungwook Choi, Pierce I-Jen Chuang, Zhuo Wang, Swagath Venkataramani, Vijayalakshmi Srinivasan, Kailash Gopalakrishnan

Deep learning algorithms achieve high classification accuracy at the expense of significant computation cost. In order to reduce this cost, several quantization schemes have gained attention recently with some focusing on weight quantization, and others focusing on quantizing activations. This paper proposes novel techniques that target weight and activation quantizations separately resulting in an overall quantized neural network (QNN). The activation quantization technique, PArameterized Clipping acTivation (PACT), uses an activation clipping parameter $\alpha$ that is optimized during training to find the right quantization scale. The weight quantization scheme, statistics-aware weight binning (SAWB), finds the optimal scaling factor that minimizes the quantization error based on the statistical characteristics of the distribution of weights without the need for an exhaustive search. The combination of PACT and SAWB results in a 2-bit QNN that achieves state-of-the-art classification accuracy (comparable to full precision networks) across a range of popular models and datasets.

📄 PDF Abstract BibTeX arXiv:1807.06964

Code (0)

등록된 구현이 없습니다.

Tasks

General ClassificationQuantization

Similar Papers 제목 키워드 기반

Sustainable LLM Inference for Edge AI: Evaluating Quantized LLMs for Energy Efficiency, Output Accuracy, and Inference Latency

2025-04-04 · Erik Johannes Husom, Arda Goknil, Merve Astekin, Lwin Khin Shar 외

Deploying Large Language Models (LLMs) on edge devices presents significant challenges due to computational constraints, memory limitations, inference speed, and energy consumption. Model quantization has emerged as a ke…

BenchmarkingGSM8KHumanEvalQuantization+2

GHN-QAT: Training Graph Hypernetworks to Predict Quantization-Robust Parameters of Unseen Limited Precision Neural Networks

2023-09-24 · Stone Yun, Alexander Wong

Graph Hypernetworks (GHN) can predict the parameters of varying unseen CNN architectures with surprisingly good accuracy at a fraction of the cost of iterative optimization. Following these successes, preliminary researc…

Quantization

A Selective Quantization Tuner for ONNX Models

2025-07-16 · Nikolaos Louloudakis, Ajitha Rajan arxiv

Quantization reduces the precision of deep neural networks to lower model size and computational demands, but often at the expense of accuracy. Fully quantized models can suffer significant accuracy degradation, and reso…

Verifying Quantized GNNs With Readout Is Decidable But Highly Intractable

2025-10-09 · Artem Chernobrovkin, Marco Sälzer, François Schwarzentruber, Nicolas Troquard arxiv

We introduce a logical language for reasoning about quantized aggregate-combine graph neural networks with global readout (ACR-GNNs). We provide a logical characterization and use it to prove that verification tasks for …

Fast Implementation of 4-bit Convolutional Neural Networks for Mobile Devices

2020-09-14 · Anton Trusov, Elena Limonova, Dmitry Slugin, Dmitry Nikolaev 외

Quantized low-precision neural networks are very popular because they require less computational resources for inference and can provide high performance, which is vital for real-time and embedded recognition systems. Ho…

Optical Character Recognition (OCR)Quantization