activity
20182021
most citedLocal and Global Uniform Convexity Conditions

5 citations · 13 across the 6 of their papers we have counts for

collaborators

12 papers

cs.LG20211 cited

Efficient Online-Bandit Strategies for Minimax Learning Problems

Christophe Roux, Elias Wirth, Sebastian Pokutta +1

Several learning problems involve solving min-max problems, e.g., empirical distributional robust learning or learning with non-standard aggregated losses. More specifically, these…

cs.LG20212 cited

Linear Bandits on Uniformly Convex Sets

Thomas Kerdreux, Christophe Roux, Alexandre d'Aspremont +1

Linear bandit algorithms yield pseudo-regret bounds on compact convex action sets and two types of structural assu…

math.OC20215 cited

Local and Global Uniform Convexity Conditions

Thomas Kerdreux, Alexandre d'Aspremont, Sebastian Pokutta

We review various characterizations of uniform convexity and smoothness on norm balls in finite-dimensional spaces and connect results stemming from the geometry of Banach spaces w…

cs.LG20211 cited

Generating Structured Adversarial Attacks Using Frank-Wolfe Method

Ehsan Kazemi, Thomas Kerdreux, Liquang Wang

White box adversarial perturbations are generated via iterative optimization algorithms most often by minimizing an adversarial loss on a neighborhood of the original imag…

math.OC20204 cited

Affine Invariant Analysis of Frank-Wolfe on Strongly Convex Sets

Thomas Kerdreux, Lewis Liu, Simon Lacoste-Julien +1

It is known that the Frank-Wolfe (FW) algorithm, which is affine-covariant, enjoys accelerated convergence rates when the constraint set is strongly convex. However, these results…

cs.GR2020

Diptychs of human and machine perceptions

Vivien Cabannes, Thomas Kerdreux, Louis Thiry

We propose visual creations that put differences in algorithms and humans \emph{perceptions} into perspective. We exploit saliency maps of neural networks and visual focus of human…