no code implementations • 21 Sep 2023 • Christiaan Lamers, Rene Vidal, Nabil Belbachir, Niki van Stein, Thomas Baeck, Paris Giampouras
A key challenge in this setting is the so-called "catastrophic forgetting problem", in which the performance of the learner in an "old task" decreases when subsequently trained on a "new task".
no code implementations • 7 Jun 2023 • Darshan Thaker, Paris Giampouras, René Vidal
In this paper, we build on prior work and propose a novel framework for reverse engineering of deceptions which supposes that the clean data lies in the range of a GAN.
no code implementations • 9 Mar 2022 • Darshan Thaker, Paris Giampouras, René Vidal
We pose this problem as a block-sparse recovery problem, where both the signal and the attack are assumed to lie in a union of subspaces that includes one subspace per class and one subspace per attack type.
no code implementations • ICLR 2022 • Paris Giampouras, Benjamin David Haeffele, Rene Vidal
In particular, we show that 1) all of the problem instances will converge to a vector in the null space of the subspace and 2) the ensemble of problem instance solutions will be sufficiently diverse to fully span the null space of the subspace (and thus reveal the true codimension of the subspace) even when the true subspace dimension is unknown.
no code implementations • 7 Apr 2015 • Paris Giampouras, Konstantinos Themelis, Athanasios Rontogiannis, Konstantinos Koutroumbas
In a plethora of applications dealing with inverse problems, e. g. in image processing, social networks, compressive sensing, biological data processing etc., the signal of interest is known to be structured in several ways at the same time.