English
Related papers

Related papers: Train Flat, Then Compress: Sharpness-Aware Minimiz…

200 papers

The unstructured sparsity after pruning poses a challenge to the efficient implementation of deep learning models in existing regular architectures like systolic arrays. On the other hand, coarse-grained structured pruning is suitable for…

Machine Learning · Computer Science 2024-11-22 Xizi Chen , Jingyang Zhu , Jingbo Jiang , Chi-Ying Tsui

Deep Neural Networks (DNNs) are applied in a wide range of usecases. There is an increased demand for deploying DNNs on devices that do not have abundant resources such as memory and computation units. Recently, network compression through…

Machine Learning · Computer Science 2020-05-19 Haichuan Yang , Shupeng Gui , Yuhao Zhu , Ji Liu

Fine-tuned transformer models have shown superior performances in many natural language tasks. However, the large model size prohibits deploying high-performance transformer models on resource-constrained devices. This paper proposes a…

Computation and Language · Computer Science 2024-10-01 Zi Yang , Samridhi Choudhary , Siegfried Kunzmann , Zheng Zhang

Sharpness-aware minimization (SAM) improves generalization of various deep learning tasks. Motivated by popular architectures such as LoRA, we explore the implicit regularization of SAM for scale-invariant problems involving two groups of…

Machine Learning · Computer Science 2024-10-22 Bingcong Li , Liang Zhang , Niao He

We consider the problem of deep neural net compression by quantization: given a large, reference net, we want to quantize its real-valued weights using a codebook with $K$ entries so that the training loss of the quantized net is minimal.…

Machine Learning · Computer Science 2017-07-17 Miguel Á. Carreira-Perpiñán , Yerlan Idelbayev

Pruning is a promising approach to compress deep learning models in order to deploy them on resource-constrained edge devices. However, many existing pruning solutions are based on unstructured pruning, which yields models that cannot…

Machine Learning · Computer Science 2023-03-16 Kaiqi Zhao , Animesh Jain , Ming Zhao

Recent progress in deep learning has been driven by increasingly larger models. However, their computational and energy demands have grown proportionally, creating significant barriers to their deployment and to a wider adoption of deep…

Machine Learning · Computer Science 2025-09-16 Pedro Savarese

Model compression methods are important to allow for easier deployment of deep learning models in compute, memory and energy-constrained environments such as mobile phones. Knowledge distillation is a class of model compression algorithm…

Computer Vision and Pattern Recognition · Computer Science 2020-12-08 Suhas Lohit , Michael Jones

Effective clinical deployment of deep learning models in healthcare demands high generalization performance to ensure accurate diagnosis and treatment planning. In recent years, significant research has focused on improving the…

Image and Video Processing · Electrical Eng. & Systems 2025-10-22 Mohamed Hassan , Aleksandar Vakanski , Min Xian

To reduce model size during post-training, compression methods, including knowledge distillation, low-rank approximation, and pruning, are often applied after fine-tuning the model. However, sequential fine-tuning and compression sacrifices…

Machine Learning · Computer Science 2025-05-29 Xiangyu Chen , Jing Liu , Ye Wang , Matthew Brand , Pu , Wang , Toshiaki Koike-Akino

Model merging has emerged as a lightweight alternative to joint multi-task learning (MTL), yet the generalization properties of merged models remain largely unexplored. Establishing such theoretical guarantees is non-trivial, as the merging…

Machine Learning · Computer Science 2025-12-25 Seyed Arshan Dalili , Mehrdad Mahdavi

In this work we present a method to improve the pruning step of the current state-of-the-art methodology to compress neural networks. The novelty of the proposed pruning technique is in its differentiability, which allows pruning to be…

Computer Vision and Pattern Recognition · Computer Science 2019-01-08 Franco Manessi , Alessandro Rozza , Simone Bianco , Paolo Napoletano , Raimondo Schettini

As Large Language Models (LLMs) continue to scale, post-training pruning has emerged as a promising approach to reduce computational costs while preserving performance. Existing methods such as SparseGPT and Wanda achieve high sparsity…

Computation and Language · Computer Science 2026-01-15 Sai Varun Kodathala , Rakesh Vunnam

Existing generalization measures that aim to capture a model's simplicity based on parameter counts or norms fail to explain generalization in overparameterized deep neural networks. In this paper, we introduce a new, theoretically…

Machine Learning · Computer Science 2021-03-11 Lorenz Kuhn , Clare Lyle , Aidan N. Gomez , Jonas Rothfuss , Yarin Gal

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…

Machine Learning · Computer Science 2026-01-30 Daniel T. Bernstein , Luca Di Carlo , David Schwab

As real-world graphs expand in size, larger GNN models with billions of parameters are deployed. High parameter count in such models makes training and inference on graphs expensive and challenging. To reduce the computational and memory…

Machine Learning · Computer Science 2023-02-27 Hongwu Peng , Deniz Gurevin , Shaoyi Huang , Tong Geng , Weiwen Jiang , Omer Khan , Caiwen Ding

While convolutional neural networks (CNN) have achieved impressive performance on various classification/recognition tasks, they typically consist of a massive number of parameters. This results in significant memory requirement as well as…

Computer Vision and Pattern Recognition · Computer Science 2019-05-14 Pravendra Singh , Vinay Kumar Verma , Piyush Rai , Vinay P. Namboodiri

Sparsifying neural networks often suffers from seemingly inevitable performance degradation, and it remains challenging to restore the original performance despite much recent progress. Motivated by recent studies in robust optimization, we…

Machine Learning · Computer Science 2025-06-17 Dongyeop Lee , Kwanhee Lee , Jinseok Chung , Namhoon Lee

Deep neural networks often have millions of parameters. This can hinder their deployment to low-end devices, not only due to high memory requirements but also because of increased latency at inference. We propose a novel model compression…

Machine Learning · Computer Science 2020-06-15 Tao Lin , Sebastian U. Stich , Luis Barba , Daniil Dmitriev , Martin Jaggi

To address the enormous size of Large Language Models (LLMs), model compression methods, such as quantization and pruning, are often deployed, especially on edge devices. In this work, we focus on layer-wise post-training quantization and…

Machine Learning · Computer Science 2025-12-02 Jing Liu , Toshiaki Koike-Akino , Ye Wang , Hassan Mansour , Matthew Brand