paper-with-me

홈 › Papers

CLIP: Cheap Lipschitz Training of Neural Networks

2021-03-23 · Leon Bungert, René Raab, Tim Roith, Leo Schwinn, Daniel Tenbrinck

Despite the large success of deep neural networks (DNN) in recent years, most neural networks still lack mathematical guarantees in terms of stability. For instance, DNNs are vulnerable to small or even imperceptible input perturbations, so called adversarial examples, that can cause false predictions. This instability can have severe consequences in applications which influence the health and safety of humans, e.g., biomedical imaging or autonomous driving. While bounding the Lipschitz constant of a neural network improves stability, most methods rely on restricting the Lipschitz constants of each layer which gives a poor bound for the actual Lipschitz constant. In this paper we investigate a variational regularization method named CLIP for controlling the Lipschitz constant of a neural network, which can easily be integrated into the training procedure. We mathematically analyze the proposed model, in particular discussing the impact of the chosen regularization parameter on the output of the network. Finally, we numerically evaluate our method on both a nonlinear regression problem and the MNIST and Fashion-MNIST classification databases, and compare our results with a weight regularization approach.

📄 PDF Abstract BibTeX arXiv:2103.12531

Code (1)

TimRoith/CLIP 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

Improved Scalable Lipschitz Bounds for Deep Neural Networks

2025-03-18 · Usman Syed, Bin Hu

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…

On the Convergence of Differentially Private Federated Learning on Non-Lipschitz Objectives, and with Normalized Client Updates

2021-06-13 · Rudrajit Das, Abolfazl Hashemi, Sujay Sanghavi, Inderjit S. Dhillon

There is a dearth of convergence results for differentially private federated learning (FL) with non-Lipschitz objective functions (i.e., when gradient norms are not bounded). The primary reason for this is that the clip…

BenchmarkingFederated LearningQuantizationSensitivity

DP-SGD Without Clipping: The Lipschitz Neural Network Way

2023-05-25 · Louis Bethune, Thomas Massena, Thibaut Boissin, Yannick Prudent 외

State-of-the-art approaches for training Differentially Private (DP) Deep Neural Networks (DNN) face difficulties to estimate tight bounds on the sensitivity of the network's layers, and instead rely on a process of per-…

Sensitivity

Beyond Uniform Lipschitz Condition in Differentially Private Optimization

2022-06-21 · Rudrajit Das, Satyen Kale, Zheng Xu, Tong Zhang 외

Most prior results on differentially private stochastic gradient descent (DP-SGD) are derived under the simplistic assumption of uniform Lipschitzness, i.e., the per-sample gradients are uniformly bounded. We generalize …

Benchmarkingregression

Stability and Convergence of Stochastic Gradient Clipping: Beyond Lipschitz Continuity and Smoothness

2021-02-12 · Vien V. Mai, Mikael Johansson

Stochastic gradient algorithms are often unstable when applied to functions that do not have Lipschitz-continuous and/or bounded gradients. Gradient clipping is a simple and effective technique to stabilize the training …