Ludovic Schwartz
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ludovic Schwartz has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Anders Jonsson
Universitat Pompeu Fabra
1 shared publication - Gergely Neu
Universitat Pompeu Fabra Barcelona Spain
1 shared publication Javier Segovia-Aguas
Universitat Pompeu Fabra Barcelona Spain
1 shared publication- Sergio Calo
Faculty of Physics, University of Santiago de Compostela (USC), 15705 Santiago de Compostela, Spain
1 shared publication
Latest Publications
- Open Access
Distances for Markov chains from sample streams
Bisimulation metrics are powerful tools for measuring similarities between stochastic processes, and specifically Markov chains. Recent advances have uncovered that bisimulation metrics are, in fact, optimal-transport distances, which has enabled the development of fast algorithms for computing such metrics with provable accuracy and runtime guarantees. However, these recent methods, as well as all previously known methods, assume full knowledge of the transition dynamics. This is often an impractical assumption in most real-world scenarios, where typically only sample trajectories are available. In this work, we propose a stochastic optimization method that addresses this limitation and estimates bisimulation metrics based on sample access, without requiring explicit transition models. Our approach is derived from a new linear programming (LP) formulation of bisimulation metrics, which we solve using a stochastic primal-dual optimization method. We provide theoretical guarantees on the sample complexity of the algorithm and validate its effectiveness through a series of empirical evaluations.
Open AccessDistances for Markov chains from sample streams
Bisimulation metrics are powerful tools for measuring similarities between stochastic processes, and specifically Markov chains. Recent advances have uncovered that bisimulation metrics are, in fact, optimal-transport distances, which has enabled the development of fast algorithms for computing such metrics with provable accuracy and runtime guarantees. However, these recent methods, as well as all previously known methods, assume full knowledge of the transition dynamics. This is often an impractical assumption in most real-world scenarios, where typically only sample trajectories are available. In this work, we propose a stochastic optimization method that addresses this limitation and estimates bisimulation metrics based on sample access, without requiring explicit transition models. Our approach is derived from a new linear programming (LP) formulation of bisimulation metrics, which we solve using a stochastic primal-dual optimization method. We provide theoretical guarantees on the sample complexity of the algorithm and validate its effectiveness through a series of empirical evaluations.