10 citations · 23 across the 4 of their papers we have counts for
5 papers
Nearly-Linear Time Private Hypothesis Selection with the Optimal Approximation Factor
Maryam Aliakbarpour, Zhan Shi, Ria Stevens +1
Estimating the density of a distribution from its samples is a fundamental problem in statistics. Hypothesis selection addresses the setting where, in addition to a sample set, we…
Stochastic optimization over proximally smooth sets
Damek Davis, Dmitriy Drusvyatskiy, Zhan Shi
We introduce a class of stochastic algorithms for minimizing weakly convex functions over proximally smooth sets. As their main building blocks, the algorithms use simplified model…
Generalised Lipschitz Regularisation Equals Distributional Robustness
Zac Cranko, Zhan Shi, Xinhua Zhang +2
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 approximat…
Lipschitz Networks and Distributional Robustness
Zac Cranko, Simon Kornblith, Zhan Shi +1
Robust risk minimisation has several advantages: it has been studied with regards to improving the generalisation properties of models and robustness to adversarial perturbation. W…
Monge blunts Bayes: Hardness Results for Adversarial Training
Zac Cranko, Aditya Krishna Menon, Richard Nock +3
The last few years have seen a staggering number of empirical studies of the robustness of neural networks in a model of adversarial perturbations of their inputs. Most rely on an…