paper-with-me

Papers

Certifying Distributional Robustness using Lipschitz Regularisation

2019-09-25 · Zac Cranko, Zhan Shi, Xinhua Zhang, Simon Kornblith, Richard Nock

Distributional robust risk (DRR) minimisation has arisen as a flexible and effective framework for machine learning. Approximate solutions based on dualisation have become particularly favorable in addressing the semi-infinite optimisation, and they also provide a certificate of the robustness for the worst-case population loss. However existing methods are restricted to either linear models or very small perturbations, and cannot find the globally optimal solution for restricted nonlinear models such as kernel methods. In this paper we resolved these limitations by upper bounding DRRs with an empirical risk regularised by the Lipschitz constant of the model, including deep neural networks and kernel methods. As an application, we showed that it also provides a certificate for adversarial training, and global solutions can be achieved on product kernel machines in polynomial time.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Generalised Lipschitz Regularisation Equals Distributional Robustness

2020-02-11 · Zac Cranko, Zhan Shi, Xinhua Zhang, Richard Nock 외

The problem of adversarial examples has highlighted the need for a theory of regularisation that is general enough to apply to exotic function classes, such as universal approximators. In response, we give a very general…

Certifying Out-of-Domain Generalization for Blackbox Functions

2022-02-03 · Maurice Weber, Linyi Li, Boxin Wang, Zhikuan Zhao 외

Certifying the robustness of model performance under bounded data distribution drifts has recently attracted intensive interest under the umbrella of distributional robustness. However, existing techniques either make st…

Domain Generalization

Certifying Robustness via Topological Representations

2025-01-18 · Jens Agerberg, Andrea Guidolin, Andrea Martinelli, Pepijn Roos Hoefgeest 외

We propose a neural network architecture that can learn discriminative geometric representations of data from persistence diagrams, common descriptors of Topological Data Analysis. The learned representations enjoy Lipsc…

Topological Data Analysis

Certifying Ensembles: A General Certification Theory with S-Lipschitzness

2023-04-25 · Aleksandar Petrov, Francisco Eiras, Amartya Sanyal, Philip H. S. Torr 외

Improving and guaranteeing the robustness of deep learning models has been a topic of intense research. Ensembling, which combines several classifiers to provide a better model, has shown to be beneficial for generalisat…

ECLipsE: Efficient Compositional Lipschitz Constant Estimation for Deep Neural Networks

2024-04-05 · Yuezhu Xu, S. Sivaranjani

The Lipschitz constant plays a crucial role in certifying the robustness of neural networks to input perturbations. Since calculating the exact Lipschitz constant is NP-hard, efforts have been made to obtain tight upper …