paper-with-me

홈 › Papers

On Lipschitz Regularization of Convolutional Layers using Toeplitz Matrix Theory

2020-06-15 · Alexandre Araujo, Benjamin Negrevergne, Yann Chevaleyre, Jamal Atif

This paper tackles the problem of Lipschitz regularization of Convolutional Neural Networks. Lipschitz regularity is now established as a key property of modern deep learning with implications in training stability, generalization, robustness against adversarial examples, etc. However, computing the exact value of the Lipschitz constant of a neural network is known to be NP-hard. Recent attempts from the literature introduce upper bounds to approximate this constant that are either efficient but loose or accurate but computationally expensive. In this work, by leveraging the theory of Toeplitz matrices, we introduce a new upper bound for convolutional layers that is both tight and easy to compute. Based on this result we devise an algorithm to train Lipschitz regularized Convolutional Neural Networks.

📄 PDF Abstract BibTeX arXiv:2006.08391

Code (2)

MILES-PSL/upper_bound_lipschitz_convolutional_layers 공식 구현 pytorch
MILES-PSL/Upper-Bound-Lipschitz-Convolutional-Layers pytorch

Similar Papers 제목 키워드 기반

Lipschitz Bound Analysis of Neural Networks

2022-07-14 · Sarosij Bose

Lipschitz Bound Estimation is an effective method of regularizing deep neural networks to make them robust against adversarial attacks. This is useful in a variety of applications ranging from reinforcement learning to a…

Rolling Shutter Correction

Efficient Bound of Lipschitz Constant for Convolutional Layers by Gram Iteration

2023-05-25 · Blaise Delattre, Quentin Barthélemy, Alexandre Araujo, Alexandre Allauzen

Since the control of the Lipschitz constant has a great impact on the training stability, generalization, and robustness of neural networks, the estimation of this value is nowadays a real scientific challenge. In this p…

Ortho-Shot: Low Displacement Rank Regularization with Data Augmentation for Few-Shot Learning

2021-10-18 · Uche Osahor, Nasser M. Nasrabadi

In few-shot classification, the primary goal is to learn representations from a few samples that generalize well for novel classes. In this paper, we propose an efficient low displacement rank (LDR) regularization strate…

Data AugmentationDiversityFew-Shot Learning

Asymptotic Singular Value Distribution of Linear Convolutional Layers

2020-06-12 · Xinping Yi

In convolutional neural networks, the linear transformation of multi-channel two-dimensional convolutional layers with linear convolution is a block matrix with doubly Toeplitz blocks. Although a "wrapping around" operat…

Lipschitz-bounded 1D convolutional neural networks using the Cayley transform and the controllability Gramian

2023-03-20 · Patricia Pauli, Ruigang Wang, Ian R. Manchester, Frank Allgöwer

We establish a layer-wise parameterization for 1D convolutional neural networks (CNNs) with built-in end-to-end robustness guarantees. In doing so, we use the Lipschitz constant of the input-output mapping characterized …