Martin Roa-Villescas
Martin Roa-Villescas earned his B.Sc. degree in Electronic Engineering from the National University of Colombia (UNAL) in Manizales, Colombia, in 2010. He received his M.Sc. degree in Embedded Systems from Eindhoven University of Technology (TU/e) in Eindhoven, The Netherlands, in 2013. Currently, he is pursuing a Ph.D. degree in Bayesian Machine Learning at TU/e. Between 2013 and 2018, he served as an embedded software designer at Philips Research in Eindhoven, The Netherlands. His research interests encompass probabilistic graphical models, open-source software, and robotics.
Session
TensorInference, a package for exact probabilistic inference in discrete graphical models, capitalizes on recent tensor network advancements. Its tensor-based engine features optimized contraction ordering methods, an aspect vital to computational performance. Additionally, it incorporates optimized BLAS routines and GPU technology for enhanced efficiency. In a comparative evaluation with similar libraries, TensorInference demonstrates superior scalability for models of increasing complexity.