Saved in:
Bibliographic Details
Main Authors: Liao, Jing-Xiao, Wang, Haoran, Li, Tao, Lyu, Daoming, Zhang, Yi, Cai, Chengjun, Fan, Feng-Lei
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.29768
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911557996249088
author Liao, Jing-Xiao
Wang, Haoran
Li, Tao
Lyu, Daoming
Zhang, Yi
Cai, Chengjun
Fan, Feng-Lei
author_facet Liao, Jing-Xiao
Wang, Haoran
Li, Tao
Lyu, Daoming
Zhang, Yi
Cai, Chengjun
Fan, Feng-Lei
contents With the development of foundational models, model compression has become a critical requirement. Various model compression approaches have been proposed such as low-rank decomposition, pruning, quantization, ergodic dynamic systems, and knowledge distillation, which are based on different heuristics. To elevate the field from fragmentation to a principled discipline, we construct a unifying mathematical framework for model compression grounded in measure theory. We further demonstrate that each model compression technique is mathematically equivalent to a neural network subject to a regularization. Building upon this mathematical and structural equivalence, we propose an experimentally-verified data-free model compression framework, termed \textit{Big2Small}, which translates Implicit Neural Representations (INRs) from data domain to the domain of network parameters. \textit{Big2Small} trains compact INRs to encode the weights of larger models and reconstruct the weights during inference. To enhance reconstruction fidelity, we introduce Outlier-Aware Preprocessing to handle extreme weight values and a Frequency-Aware Loss function to preserve high-frequency details. Experiments on image classification and segmentation demonstrate that \textit{Big2Small} achieves competitive accuracy and compression ratios compared to state-of-the-art baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2603_29768
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Big2Small: A Unifying Neural Network Framework for Model Compression
Liao, Jing-Xiao
Wang, Haoran
Li, Tao
Lyu, Daoming
Zhang, Yi
Cai, Chengjun
Fan, Feng-Lei
Machine Learning
With the development of foundational models, model compression has become a critical requirement. Various model compression approaches have been proposed such as low-rank decomposition, pruning, quantization, ergodic dynamic systems, and knowledge distillation, which are based on different heuristics. To elevate the field from fragmentation to a principled discipline, we construct a unifying mathematical framework for model compression grounded in measure theory. We further demonstrate that each model compression technique is mathematically equivalent to a neural network subject to a regularization. Building upon this mathematical and structural equivalence, we propose an experimentally-verified data-free model compression framework, termed \textit{Big2Small}, which translates Implicit Neural Representations (INRs) from data domain to the domain of network parameters. \textit{Big2Small} trains compact INRs to encode the weights of larger models and reconstruct the weights during inference. To enhance reconstruction fidelity, we introduce Outlier-Aware Preprocessing to handle extreme weight values and a Frequency-Aware Loss function to preserve high-frequency details. Experiments on image classification and segmentation demonstrate that \textit{Big2Small} achieves competitive accuracy and compression ratios compared to state-of-the-art baselines.
title Big2Small: A Unifying Neural Network Framework for Model Compression
topic Machine Learning
url https://arxiv.org/abs/2603.29768