paper-with-me

홈 › Papers

Soft Quantization: Model Compression Via Weight Coupling

2026-01-29 · Daniel T. Bernstein, Luca Di Carlo, David Schwab arxiv

We show that introducing short-range attractive couplings between the weights of a neural network during training provides a novel avenue for model quantization. These couplings rapidly induce the discretization of a model's weight distribution, and they do so in a mixed-precision manner despite only relying on two additional hyperparameters. We demonstrate that, within an appropriate range of hyperparameters, our "soft quantization'' scheme outperforms histogram-equalized post-training quantization on ResNet-20/CIFAR-10. Soft quantization provides both a new pipeline for the flexible compression of machine learning models and a new tool for investigating the trade-off between compression and generalization in high-dimensional loss landscapes.

📄 PDF Abstract BibTeX arXiv:2601.21219

Code (0)

등록된 구현이 없습니다.

Tasks

Model Compression

Similar Papers 제목 키워드 기반

R2 Loss: Range Restriction Loss for Model Compression and Quantization

2023-03-14 · Arnav Kundu, Chungkuk Yoo, Srijan Mishra, Minsik Cho 외

Model quantization and compression is widely used techniques to reduce usage of computing resource at inference time. While state-of-the-art works have been achieved reasonable accuracy with higher bit such as 4bit or 8b…

ClassificationModel CompressionModel OptimizationQuantization

Soft Weight-Sharing for Neural Network Compression

2017-02-13 · Karen Ullrich, Edward Meeds, Max Welling

The success of deep learning in numerous application domains created the de- sire to run and train them on mobile devices. This however, conflicts with their computationally, memory and energy intense nature, leading to …

Neural Network CompressionQuantization

Compact Token Representations with Contextual Quantization for Efficient Document Re-ranking

2022-03-29 · ACL 2022 5 · Yingrui Yang, Yifan Qiao, Tao Yang

Transformer based re-ranking models can achieve high search relevance through context-aware soft matching of query tokens with document tokens. To alleviate runtime complexity of such inference, previous work has adopted…

QuantizationRe-Ranking

Compact Token Representations with Contextual Quantization for Efficient Document Re-ranking

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Transformer based re-ranking models can achieve high search relevance through context-aware soft matching of query tokens with document tokens. To alleviate runtime complexity of such inference, previous work has adopte…

QuantizationRe-Ranking

A flexible, extensible software framework for model compression based on the LC algorithm

2020-05-15 · Yerlan Idelbayev, Miguel Á. Carreira-Perpiñán

We propose a software framework based on the ideas of the Learning-Compression (LC) algorithm, that allows a user to compress a neural network or other machine learning model using different compression schemes with mini…

BIG-bench Machine LearningLow-rank compressionModel CompressionNetwork Pruning+1