Scalable Lipschitz Estimation for CNNs
Estimating the Lipschitz constant of deep neural networks is of growing interest as it is useful for informing on generalisability and adversarial robustness. Convolutional neural networks (CNNs) in particular, underpin much of the recent success in computer vision related applications. However, although existing methods for estimating the Lipschitz constant can be tight, they have limited scalability when applied to CNNs. To tackle this, we propose a novel method to accelerate Lipschitz constant estimation for CNNs. The core idea is to divide a large convolutional block via a joint layer and width-wise partition, into a collection of smaller blocks. We prove an upper-bound on the Lipschitz constant of the larger block in terms of the Lipschitz constants of the smaller blocks. Through varying the partition factor, the resulting method can be adjusted to prioritise either accuracy or scalability and permits parallelisation. We demonstrate an enhanced scalability and comparable accuracy to existing baselines through a range of experiments.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial RobustnessSimilar Papers 제목 키워드 기반
Improved Scalable Lipschitz Bounds for Deep Neural Networks
Computing tight Lipschitz bounds for deep neural networks is crucial for analyzing their robustness and stability, but existing approaches either produce relatively conservative estimates or rely on semidefinite programm…
Lipschitz Bound Analysis of Neural Networks
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 CorrectionLipschitz constant estimation for 1D convolutional neural networks
In this work, we propose a dissipativity-based method for Lipschitz constant estimation of 1D convolutional neural networks (CNNs). In particular, we analyze the dissipativity properties of convolutional, pooling, and fu…
On Lipschitz Bounds of General Convolutional Neural Networks
Many convolutional neural networks (CNNs) have a feed-forward structure. In this paper, a linear program that estimates the Lipschitz bound of such CNNs is proposed. Several CNNs, including the scattering networks, the A…
Lipschitz-bounded 1D convolutional neural networks using the Cayley transform and the controllability Gramian
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 …