English
Related papers

Related papers: Understanding Learning Invariance in Deep Linear N…

200 papers

Contrary to most machine learning models, modern deep artificial neural networks typically include multiple components that contribute to regularization. Despite the fact that some (explicit) regularization techniques, such as weight decay…

Computer Vision and Pattern Recognition · Computer Science 2020-11-13 Alex Hernández-García , Peter König

Recent works have highlighted scale invariance or symmetry present in the weight space of a typical deep network and the adverse effect it has on the Euclidean gradient based stochastic gradient descent optimization. In this work, we show…

Machine Learning · Computer Science 2015-11-04 Vijay Badrinarayanan , Bamdev Mishra , Roberto Cipolla

Using weight decay to penalize the L2 norms of weights in neural networks has been a standard training practice to regularize the complexity of networks. In this paper, we show that a family of regularizers, including weight decay, is…

Machine Learning · Computer Science 2022-06-09 Ziquan Liu , Yufei Cui , Antoni B. Chan

It has been experimentally observed in recent years that multi-layer artificial neural networks have a surprising ability to generalize, even when trained with far more parameters than observations. Is there a theoretical basis for this?…

Machine Learning · Statistics 2018-09-19 Andrew R. Barron , Jason M. Klusowski

Deep neural networks (DNNs) have become increasingly important due to their excellent empirical performance on a wide range of problems. However, regularization is generally achieved by indirect means, largely due to the complex set of…

Machine Learning · Computer Science 2018-07-02 Amal Rannen Triki , Maxim Berman , Matthew B. Blaschko

Despite apparent human-level performances of deep neural networks (DNN), they behave fundamentally differently from humans. They easily change predictions when small corruptions such as blur and noise are applied on the input (lack of…

Computer Vision and Pattern Recognition · Computer Science 2020-03-10 Sanghyuk Chun , Seong Joon Oh , Sangdoo Yun , Dongyoon Han , Junsuk Choe , Youngjoon Yoo

Equivariance w.r.t. geometric transformations in neural networks improves data efficiency, parameter efficiency and robustness to out-of-domain perspective shifts. When equivariance is not designed into a neural network, the network can…

Computer Vision and Pattern Recognition · Computer Science 2023-04-10 Robert-Jan Bruintjes , Tomasz Motyka , Jan van Gemert

Though data augmentation has become a standard component of deep neural network training, the underlying mechanism behind the effectiveness of these techniques remains poorly understood. In practice, augmentation policies are often chosen…

Machine Learning · Computer Science 2020-06-08 Raphael Gontijo-Lopes , Sylvia J. Smullin , Ekin D. Cubuk , Ethan Dyer

Machine learning techniques for the solution of inverse problems have become an attractive approach in the last decade, while their theoretical foundations are still in their infancy. In this chapter we want to pursue the study of…

Numerical Analysis · Mathematics 2025-12-10 Martin Burger , Samira Kabri , Gitta Kutyniok , Yunseok Lee , Lukas Weigand

Regularization is typically understood as improving generalization by altering the landscape of local extrema to which the model eventually converges. Deep neural networks (DNNs), however, challenge this view: We show that removing…

Machine Learning · Computer Science 2019-06-03 Aditya Golatkar , Alessandro Achille , Stefano Soatto

Data augmentation is commonly used to encode invariances in learning methods. However, this process is often performed in an inefficient manner, as artificial examples are created by applying a number of transformations to all points in the…

Machine Learning · Computer Science 2019-03-04 Michael Kuchnik , Virginia Smith

Dense depth and surface normal predictors should possess the equivariant property to cropping-and-resizing -- cropping the input image should result in cropping the same output image. However, we find that state-of-the-art depth and normal…

Computer Vision and Pattern Recognition · Computer Science 2023-10-18 Yuanyi Zhong , Anand Bhattad , Yu-Xiong Wang , David Forsyth

Data augmentation is popular in the training of large neural networks; currently, however, there is no clear theoretical comparison between different algorithmic choices on how to use augmented data. In this paper, we take a step in this…

Machine Learning · Computer Science 2022-06-17 Shuo Yang , Yijun Dong , Rachel Ward , Inderjit S. Dhillon , Sujay Sanghavi , Qi Lei

Computer vision research has long aimed to build systems that are robust to spatial transformations found in natural data. Traditionally, this is done using data augmentation or hard-coding invariances into the architecture. However, too…

Computer Vision and Pattern Recognition · Computer Science 2024-02-19 Utkarsh Singhal , Carlos Esteves , Ameesh Makadia , Stella X. Yu

This paper is motivated by an open problem around deep networks, namely, the apparent absence of over-fitting despite large over-parametrization which allows perfect fitting of the training data. In this paper, we analyze this phenomenon in…

Machine Learning · Computer Science 2019-08-28 Hrushikesh Mhaskar , Tomaso Poggio

Inverse problems arise in a number of domains such as medical imaging, remote sensing, and many more, relying on the use of advanced signal and image processing approaches -- such as sparsity-driven techniques -- to determine their…

Machine Learning · Computer Science 2019-02-01 Jaweria Amjad , Zhaoyan Lyu , Miguel R. D. Rodrigues

With a goal of understanding what drives generalization in deep networks, we consider several recently suggested explanations, including norm-based control, sharpness and robustness. We study how these measures can ensure generalization,…

Machine Learning · Computer Science 2017-07-07 Behnam Neyshabur , Srinadh Bhojanapalli , David McAllester , Nathan Srebro

When fine-tuning Deep Neural Networks (DNNs) to new data, DNNs are prone to overwriting network parameters required for task-specific functionality on previously learned tasks, resulting in a loss of performance on those tasks. We propose…

Machine Learning · Computer Science 2025-01-22 Christopher Angelini , Nidhal Bouaynaya

Inertial sensors are integral components in numerous applications, powering crucial features in robotics and our daily lives. In recent years, deep learning has significantly advanced inertial sensing performance and robustness.…

Robotics · Computer Science 2026-03-03 Victoria Khalfin Fekson , Nitsan Pri-Hadash , Netta Palez , Aviad Etzion , Itzik Klein

In recent years, a variety of normalization methods have been proposed to help train neural networks, such as batch normalization (BN), layer normalization (LN), weight normalization (WN), group normalization (GN), etc. However,…

Machine Learning · Computer Science 2020-06-17 Jiacheng Sun , Xiangyong Cao , Hanwen Liang , Weiran Huang , Zewei Chen , Zhenguo Li