no code implementations • 30 Jan 2023 • Alexis de Colnet, Pierre Marquis
We consider the problem EnumIP of enumerating prime implicants of Boolean functions represented by decision decomposable negation normal form (dec-DNNF) circuits.
no code implementations • 16 Sep 2022 • Gilles Audemard, Jean-Marie Lagniez, Pierre Marquis, Nicolas Szczepanski
However, the generation of such well-founded explanations is intractable in the general case.
no code implementations • 17 Jun 2022 • Sylvie Coste-Marquis, Pierre Marquis
We elaborate on the notion of rectification of a Boolean classifier $\Sigma$.
no code implementations • 11 Feb 2022 • Pierre Bourhis, Laurence Duchien, Jérémie Dusart, Emmanuel Lonca, Pierre Marquis, Clément Quinton
Under the same assumption, we present a pseudo polynomial-time algorithm that transforms $C$ into a d-DNNF circuit $C'$ satisfied exactly by the models of $C$ having a value among the top-$k$ ones.
no code implementations • 23 Aug 2021 • Adnan Darwiche, Pierre Marquis
This leads to a refinement of quantified Boolean logic with literal quantification as its primitive.
no code implementations • NeurIPS 2021 • Gilles Audemard, Steve Bellart, Louenas Bounia, Frédéric Koriche, Jean-Marie Lagniez, Pierre Marquis
Notably, as an alternative to sufficient reasons taking the form of prime implicants of the random forest, we introduce majoritary reasons which are prime implicants of a strict majority of decision trees.
no code implementations • NeurIPS 2021 • Gilles Audemard, Steve Bellart, Louenas Bounia, Frédéric Koriche, Jean-Marie Lagniez, Pierre Marquis
We finally show that, unlike sufficient reasons, the set of all contrastive explanations for an instance given a decision tree can be derived, minimized and counted in polynomial time.
no code implementations • 13 Apr 2021 • Gilles Audemard, Steve Bellart, Louenas Bounia, Frédéric Koriche, Jean-Marie Lagniez, Pierre Marquis
In this paper, we investigate the computational intelligibility of Boolean classifiers, characterized by their ability to answer XAI queries in polynomial time.
no code implementations • 8 Dec 2020 • Danel Le Berre, Pierre Marquis, Stefan Mengel, Romain Wallon
Learning pseudo-Boolean (PB) constraints in PB solvers exploiting cutting planes based inference is not as well understood as clause learning in conflict-driven clause learning solvers.
no code implementations • 9 May 2020 • Daniel Le Berre, Pierre Marquis, Romain Wallon
While none of them performs better than the others on all benchmarks, applying weakening on the conflict side has surprising good performance, whereas applying partial weakening and division on both the conflict and the reason sides provides the best results overall.
no code implementations • 24 Oct 2014 • Daniel Le Berre, Emmanuel Lonca, Pierre Marquis
When the set of feasible solutions under consideration is of combinatorial nature and described in an implicit way as a set of constraints, optimization is typically NP-hard.