paper-with-me

Papers

Generalised Lipschitz Regularisation Equals Distributional Robustness

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

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 equality result regarding the relationship between distributional robustness and regularisation, as defined with a transportation cost uncertainty set. The theory allows us to (tightly) certify the robustness properties of a Lipschitz-regularised model with very mild assumptions. As a theoretical application we show a new result explicating the connection between adversarial learning and distributional robustness. We then give new results for how to achieve Lipschitz regularisation of kernel classifiers, which are demonstrated experimentally.

📄 PDF Abstract BibTeX arXiv:2002.04197

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Certifying Distributional Robustness using Lipschitz Regularisation

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

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-in…

Lipschitz Networks and Distributional Robustness

2018-09-04 · Zac Cranko, Simon Kornblith, Zhan Shi, Richard Nock

Robust risk minimisation has several advantages: it has been studied with regards to improving the generalisation properties of models and robustness to adversarial perturbation. We bound the distributionally robust risk…

The jump set under geometric regularisation. Part 1: Basic technique and first-order denoising

2014-07-06 · Tuomo Valkonen

Let $u \in \mbox{BV}(\Omega)$ solve the total variation denoising problem with $L^2$-squared fidelity and data $f$. Caselles et al. [Multiscale Model. Simul. 6 (2008), 879--894] have shown the containment $\mathcal{H}^{m…

Denoising

Generalised Mutual Information for Discriminative Clustering

2022-10-12 · Louis Ohl, Pierre-Alexandre Mattei, Charles Bouveyron, Warith Harchaoui 외

In the last decade, recent successes in deep clustering majorly involved the mutual information (MI) as an unsupervised objective for training neural networks with increasing regularisations. While the quality of the reg…

ClusteringDeep Clustering

Generalised Mutual Information: a Framework for Discriminative Clustering

2023-09-06 · Louis Ohl, Pierre-Alexandre Mattei, Charles Bouveyron, Warith Harchaoui 외

In the last decade, recent successes in deep clustering majorly involved the Mutual Information (MI) as an unsupervised objective for training neural networks with increasing regularisations. While the quality of the reg…

ClusteringDeep Clustering