Guillermo Alberto Perez
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Guillermo Alberto Perez has a total of 137 co-authors. Here are the top co-authors by number of shared publications:
- Jean-François Raskin
Universite Libre de Bruxelles
16 shared publications - Véronique Bruyère
University of Mons
8 shared publications - Gaëtan Staquet
Centre Inria de l’Université de Rennes
7 shared publications - Michaël Cadilhac
DePaul University
7 shared publications Ocan Sankur
CNRS, IRISA
6 shared publicationsRomain Brenguier
University of Oxford
6 shared publications
Latest Publications
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Embedded Systems Letters
- Vol. 18 (5) , 397-400
SIMD-Accelerated Parity Game Solving for Formal Verification via Strahler Progress Measures
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Embedded Systems Letters
- Vol. 18 (5) , 397-400
SIMD-Accelerated Parity Game Solving for Formal Verification via Strahler Progress Measures
- 2 July 2026
- Published by Springer Nature
- p. 127-144
Taylor’s DAgger: Verified Integration for Efficient Imitation-Learning of an MPC
- 2 July 2026
- Published by Springer Nature
- p. 127-144
Taylor’s DAgger: Verified Integration for Efficient Imitation-Learning of an MPC
- 6 June 2026
- Published by Springer Nature
- p. 194-208
Visibly Recursive Automata
- 26 October 2025
- Published by Springer Nature
- p. 425-446
Data Structures for Finite Downsets of Natural Vectors: Theory and Practice
- 26 October 2025
- Published by Springer Nature
- p. 425-446
Data Structures for Finite Downsets of Natural Vectors: Theory and Practice
- Open Access
- 21 October 2025
- Published by IOS Press
- p. 4832-4839
Data-Efficient Safe Policy Improvement Using Parametric Structure
Safe policy improvement (SPI) is an offline reinforcement learning problem in which a new policy that reliably outperforms the behavior policy with high confidence needs to be computed using only a dataset and the behavior policy. Markov decision processes (MDPs) are the standard formalism for modeling environments in SPI. In many applications, additional information in the form of parametric dependencies between distributions in the transition dynamics is available. We make SPI more data-efficient by leveraging these dependencies through three contributions: (1) a parametric SPI algorithm that exploits known correlations between distributions to more accurately estimate the transition dynamics using the same amount of data; (2) a preprocessing technique that prunes redundant actions from the environment through a game-based abstraction; and (3) a more advanced preprocessing technique, based on satisfiability modulo theory (SMT) solving, that can identify more actions to prune. Empirical results and an ablation study show that our techniques increase the data efficiency of SPI by multiple orders of magnitude while maintaining the same reliability guarantees.
- 21 October 2025
- Published by IOS Press
- p. 4832-4839
Open AccessData-Efficient Safe Policy Improvement Using Parametric Structure
Safe policy improvement (SPI) is an offline reinforcement learning problem in which a new policy that reliably outperforms the behavior policy with high confidence needs to be computed using only a dataset and the behavior policy. Markov decision processes (MDPs) are the standard formalism for modeling environments in SPI. In many applications, additional information in the form of parametric dependencies between distributions in the transition dynamics is available. We make SPI more data-efficient by leveraging these dependencies through three contributions: (1) a parametric SPI algorithm that exploits known correlations between distributions to more accurately estimate the transition dynamics using the same amount of data; (2) a preprocessing technique that prunes redundant actions from the environment through a game-based abstraction; and (3) a more advanced preprocessing technique, based on satisfiability modulo theory (SMT) solving, that can identify more actions to prune. Empirical results and an ablation study show that our techniques increase the data efficiency of SPI by multiple orders of magnitude while maintaining the same reliability guarantees.
- Open Access
- 24 June 2025
- Published by Centre pour la Communication Scientifique Directe (CCSD) in Logical Methods in Computer Science
- Vol. ume 21, Is
Algorithms for Markov Binomial Chains
We study algorithms to analyze a particular class of Markov population processes that is often used in epidemiology. More specifically, Markov binomial chains are the model that arises from stochastic time-discretizations of classical compartmental models. In this work we formalize this class of Markov population processes and focus on the problem of computing the expected time to termination in a given such model. Our theoretical contributions include proving that Markov binomial chains whose flow of individuals through compartments is acyclic almost surely terminate. We give a PSPACE algorithm for the problem of approximating the time to termination and a direct algorithm for the exact problem in the Blum-Shub-Smale model of computation. Finally, we provide a natural encoding of Markov binomial chains into a common input language for probabilistic model checkers. We implemented the latter encoding and present some initial empirical results showcasing what formal methods can do for practicing epidemiologists.
- 24 June 2025
- Published by Centre pour la Communication Scientifique Directe (CCSD) in Logical Methods in Computer Science
- Vol. ume 21, Is
Open AccessAlgorithms for Markov Binomial Chains
We study algorithms to analyze a particular class of Markov population processes that is often used in epidemiology. More specifically, Markov binomial chains are the model that arises from stochastic time-discretizations of classical compartmental models. In this work we formalize this class of Markov population processes and focus on the problem of computing the expected time to termination in a given such model. Our theoretical contributions include proving that Markov binomial chains whose flow of individuals through compartments is acyclic almost surely terminate. We give a PSPACE algorithm for the problem of approximating the time to termination and a direct algorithm for the exact problem in the Blum-Shub-Smale model of computation. Finally, we provide a natural encoding of Markov binomial chains into a common input language for probabilistic model checkers. We implemented the latter encoding and present some initial empirical results showcasing what formal methods can do for practicing epidemiologists.
- 31 March 2025
- Published by Elsevier in Information and Computation
- Vol. 304
The geometry of reachability in continuous vector addition systems with states
- 31 March 2025
- Published by Elsevier in Information and Computation
- Vol. 304
The geometry of reachability in continuous vector addition systems with states
- Open Access
Data Structures for Finite Downsets of Natural Vectors: Theory and Practice
Manipulating downward-closed sets of vectors forms the basis of so-called antichain-based algorithms in verification. In that context, the dimension of the vectors is intimately tied to the size of the input structure to be verified. In this work, we formally analyze the complexity of classical list-based algorithms to manipulate antichains as well as that of Zampuniéris's sharing trees and traditional and novel kdtree-based antichain algorithms. In contrast to the existing literature, and to better address the needs of formal verification, our analysis of \kdtree algorithms does not assume that the dimension of the vectors is fixed. Our theoretical results show that kdtrees are asymptotically better than both list- and sharing-tree-based algorithms, as an antichain data structure, when the antichains become exponentially larger than the dimension of the vectors. We evaluate this on applications in the synthesis of reactive systems from linear-temporal logic and parity-objective specifications, and establish empirically that current benchmarks for these computational tasks do not lead to a favorable situation for current implementations of kdtrees.
Open AccessData Structures for Finite Downsets of Natural Vectors: Theory and Practice
Manipulating downward-closed sets of vectors forms the basis of so-called antichain-based algorithms in verification. In that context, the dimension of the vectors is intimately tied to the size of the input structure to be verified. In this work, we formally analyze the complexity of classical list-based algorithms to manipulate antichains as well as that of Zampuniéris's sharing trees and traditional and novel kdtree-based antichain algorithms. In contrast to the existing literature, and to better address the needs of formal verification, our analysis of \kdtree algorithms does not assume that the dimension of the vectors is fixed. Our theoretical results show that kdtrees are asymptotically better than both list- and sharing-tree-based algorithms, as an antichain data structure, when the antichains become exponentially larger than the dimension of the vectors. We evaluate this on applications in the synthesis of reactive systems from linear-temporal logic and parity-objective specifications, and establish empirically that current benchmarks for these computational tasks do not lead to a favorable situation for current implementations of kdtrees.
- 13 November 2024
- Published by Springer Nature
- p. 145-165
Analyzing Value Functions of States in Parametric Markov Chains
- 13 November 2024
- Published by Springer Nature
- p. 145-165
Analyzing Value Functions of States in Parametric Markov Chains