1 citations · 2 across the 22 of their papers we have counts for
3 papers · 1 filter
A study of convex convex-composite functions via infimal convolution with applications
James V. Burke, Tim Hoheisel, Quang V. Nguyen
In this note we provide a full conjugacy and subdifferential calculus for convex convex-composite functions in finite-dimensional space. Our approach, based on infimal convolution…
A principled approach for generating adversarial images under non-smooth dissimilarity metrics
Aram-Alexandre Pooladian, Chris Finlay, Tim Hoheisel +1
Deep neural networks perform well on real world data but are prone to adversarial perturbations: small changes in the input easily lead to misclassification. In this work, we propo…
Sufficient Conditions for Metric Subregularity of Constraint Systems with Applications to Disjunctive and Ortho-Disjunctive Programs
Matúš Benko, Michal Červinka, Tim Hoheisel
This paper is devoted to the study of the metric subregularity constraint qualification (MSCQ) for general optimization problems, with the emphasis on the nonconvex setting. We ela…