English
Related papers

Related papers: Compression Implies Generalization

200 papers

Dimensionality reduction, a form of compression, can simplify representations of information to increase efficiency and reveal general patterns. Yet, this simplification also forfeits information, thereby reducing representational capacity.…

We consider the optimization of deep convolutional neural networks (CNNs) such that they provide good performance while having reduced complexity if deployed on either conventional systems utilizing spatial-domain convolution or lower…

Computer Vision and Pattern Recognition · Computer Science 2018-10-30 Yoojin Choi , Mostafa El-Khamy , Jungwon Lee

Lossy compression introduces complex compression artifacts, particularly the blocking artifacts, ringing effects and blurring. Existing algorithms either focus on removing blocking artifacts and produce blurred output, or restores sharpened…

Computer Vision and Pattern Recognition · Computer Science 2015-04-28 Chao Dong , Yubin Deng , Chen Change Loy , Xiaoou Tang

We study regularization in the context of small sample-size learning with over-parameterized neural networks. Specifically, we shift focus from architectural properties, such as norms on the network weights, to properties of the internal…

Machine Learning · Computer Science 2021-05-18 Christoph D. Hofer , Florian Graf , Marc Niethammer , Roland Kwitt

The extensive adoption of Deep Neural Networks has led to their increased utilization in challenging scientific visualization tasks. Recent advancements in building compressed data models using implicit neural representations have shown…

Machine Learning · Computer Science 2025-10-20 Abhay Kumar Dwivedi , Shanu Saklani , Soumya Dutta

We propose a new bound for generalization of neural networks using Koopman operators. Whereas most of existing works focus on low-rank weight matrices, we focus on full-rank weight matrices. Our bound is tighter than existing norm-based…

Machine Learning · Computer Science 2024-03-19 Yuka Hashimoto , Sho Sonoda , Isao Ishikawa , Atsushi Nitanda , Taiji Suzuki

We propose a general framework for neural network compression that is motivated by the Minimum Description Length (MDL) principle. For that we first derive an expression for the entropy of a neural network, which measures its complexity…

Machine Learning · Computer Science 2018-12-20 Simon Wiedemann , Arturo Marban , Klaus-Robert Müller , Wojciech Samek

Despite their high accuracy, complex neural networks demand significant computational resources, posing challenges for deployment on resource constrained devices such as mobile phones and embedded systems. Compression algorithms have been…

Machine Learning · Computer Science 2025-09-23 Ali Aghababaei-Harandi , Massih-Reza Amini

Overparameterized networks trained to convergence have shown impressive performance in domains such as computer vision and natural language processing. Pushing state of the art on salient tasks within these domains corresponds to these…

Machine Learning · Computer Science 2020-08-04 James O' Neill

For linear classifiers, the relationship between (normalized) output margin and generalization is captured in a clear and simple bound -- a large output margin implies good generalization. Unfortunately, for deep models, this relationship…

Machine Learning · Computer Science 2021-06-17 Colin Wei , Tengyu Ma

Neural networks have been shown to be vulnerable against minor adversarial perturbations of their inputs, especially for high dimensional data under $\ell_\infty$ attacks. To combat this problem, techniques like adversarial training have…

Machine Learning · Computer Science 2019-06-04 Emilio Rafael Balda , Arash Behboodi , Niklas Koep , Rudolf Mathar

The remarkable successes of deep learning models across various applications have resulted in the design of deeper networks that can solve complex problems. However, the increasing depth of such models also results in a higher storage and…

Machine Learning · Computer Science 2016-11-03 Bharat Bhusan Sau , Vineeth N. Balasubramanian

It is widely observed that deep learning models with learned parameters generalize well, even with much more model parameters than the number of training samples. We systematically investigate the underlying reasons why deep neural networks…

Machine Learning · Computer Science 2017-11-29 Lei Wu , Zhanxing Zhu , Weinan E

Machine Learning models should ideally be compact and robust. Compactness provides efficiency and comprehensibility whereas robustness provides resilience. Both topics have been studied in recent years but in isolation. Here we present a…

Machine Learning · Computer Science 2021-03-16 Omri Armstrong , Ran Gilad-Bachrach

Many applications from camera arrays to sensor networks require efficient compression and processing of correlated data, which in general is collected in a distributed fashion. While information-theoretic foundations of distributed…

Information Theory · Computer Science 2024-02-14 Ezgi Ozyilkan , Elza Erkip

Deep neural network pruning and quantization techniques have demonstrated it is possible to achieve high levels of compression with surprisingly little degradation to test set accuracy. However, this measure of performance conceals…

Machine Learning · Computer Science 2021-09-07 Sara Hooker , Aaron Courville , Gregory Clark , Yann Dauphin , Andrea Frome

We introduce a conditional compression problem and propose a fast framework for tackling it. The problem is how to quickly compress a pretrained large neural network into optimal smaller networks given target contexts, e.g. a context…

Machine Learning · Computer Science 2022-05-16 Phuoc Nguyen , Truyen Tran , Ky Le , Sunil Gupta , Santu Rana , Dang Nguyen , Trong Nguyen , Shannon Ryan , Svetha Venkatesh

Increasing the model capacity is a known approach to enhance the adversarial robustness of deep learning networks. On the other hand, various model compression techniques, including pruning and quantization, can reduce the size of the…

Machine Learning · Computer Science 2023-11-28 Svetlana Pavlitska , Hannes Grolig , J. Marius Zöllner

Understanding the generalization properties of neural networks on simple input-output distributions is key to explaining their performance on real datasets. The classical teacher-student setting, where a network is trained on data generated…

Disordered Systems and Neural Networks · Physics 2026-03-26 Rodrigo Pérez Ortiz , Gibbs Nwemadji , Jean Barbier , Federica Gerace , Alessandro Ingrosso , Clarissa Lauditi , Enrico M. Malatesta

This paper considers the subject of information losses arising from the finite datasets used in the training of neural classifiers. It proves a relationship between such losses as the product of the expected total variation of the estimated…

Machine Learning · Computer Science 2020-01-09 Brandon Foggo , Nanpeng Yu , Jie Shi , Yuanqi Gao