paper-with-me

홈 › Papers

Mixed-Precision Neural Networks: A Survey

2022-08-11 · Mariam Rakka, Mohammed E. Fouda, Pramod Khargonekar, Fadi Kurdahi

Mixed-precision Deep Neural Networks achieve the energy efficiency and throughput needed for hardware deployment, particularly when the resources are limited, without sacrificing accuracy. However, the optimal per-layer bit precision that preserves accuracy is not easily found, especially with the abundance of models, datasets, and quantization techniques that creates an enormous search space. In order to tackle this difficulty, a body of literature has emerged recently, and several frameworks that achieved promising accuracy results have been proposed. In this paper, we start by summarizing the quantization techniques used generally in literature. Then, we present a thorough survey of the mixed-precision frameworks, categorized according to their optimization techniques such as reinforcement learning and quantization techniques like deterministic rounding. Furthermore, the advantages and shortcomings of each framework are discussed, where we present a juxtaposition. We finally give guidelines for future mixed-precision frameworks.

📄 PDF Abstract BibTeX arXiv:2208.06064

Code (0)

등록된 구현이 없습니다.

Tasks

QuantizationReinforcement Learning (RL)Survey

Similar Papers 제목 키워드 기반

Mixed-Precision Quantization for Language Models: Techniques and Prospects

2025-10-19 · Mariam Rakka, Marios Fournarakis, Olga Krestinskaya, Jinane Bazzi 외 arxiv

The rapid scaling of language models (LMs) has resulted in unprecedented computational, memory, and energy requirements, making their training and deployment increasingly unsustainable. Quantization has emerged as an ess…

Effective and Efficient Mixed Precision Quantization of Speech Foundation Models

2025-01-07 · Haoning Xu, Zhaoqing Li, Zengrui Jin, Huimeng Wang 외

This paper presents a novel mixed-precision quantization approach for speech foundation models that tightly integrates mixed-precision learning and quantized model parameter estimation into one single model compression s…

Model Compressionparameter estimationQuantization

MetaMix: Meta-state Precision Searcher for Mixed-precision Activation Quantization

2023-11-12 · Han-Byul Kim, Joo Hyung Lee, Sungjoo Yoo, Hong-Seok Kim

Mixed-precision quantization of efficient networks often suffer from activation instability encountered in the exploration of bit selections. To address this problem, we propose a novel method called MetaMix which consis…

Quantization

MPX: Mixed Precision Training for JAX

2025-07-04 · Alexander Gräfe, Sebastian Trimpe arxiv

Mixed-precision training has emerged as an indispensable tool for enhancing the efficiency of neural network training in recent years. Concurrently, JAX has grown in popularity as a versatile machine learning toolbox. Ho…

Embedding Compression in Recommender Systems: A Survey

2024-08-05 · Shiwei Li, Huifeng Guo, Xing Tang, Ruiming Tang 외

To alleviate the problem of information explosion, recommender systems are widely deployed to provide personalized information filtering services. Usually, embedding tables are employed in recommender systems to transfor…

Recommendation SystemsSurvey