Germán Bassi Ericsson |
I am currently a researcher at Ericsson Research (Area Networks) working on future wireless technologies. I was previously a postdoctoral researcher in the Division of Information Science and Engineering (previously Dept. of Communication Theory) at KTH Royal Institute of Technology. Before joining KTH, I received the B.Sc. and M.Sc. degrees in Electrical Engineering in 2010 from the University of Buenos Aires, Argentina, and the Ph.D. degree in Telecommunications in 2015 from CentraleSupélec (formerly Supélec), France. My Ph.D. was done under the supervision of Prof. Pablo Piantanida and Prof. Sheng Yang.
My research interests include wireless communications, multi-user information theory, physical-layer security, and inference and statistics, with applications to privacy and machine learning.
[2021/09/28] Our paper “Tighter expected generalization error bounds via Wasserstein distance” has been accepted for presentation at NeurIPS 2021. Check the latest version in arXiv.
[2021/09/23] Our paper “Machine Learning Based C-DRX Configuration Optimization for 5G” has been accepted for presentation at MKT 2021.
[2021/08/27] Our paper “Upper Bounds on the Generalization Error of Private Algorithms for Discrete Data” has been accepted for publication in the IEEE Transactions on Information Theory (DOI).
[2021/07/24] Borja Rodríguez-Gálvez is presenting results from our paper “Tighter Expected Generalization Error Bounds via Wasserstein Distance” at the Workshop on Information-Theoretic Methods for Rigorous, Responsible, and Reliable Machine Learning at ICML 2021.
[2021/05/18] Our paper, “Neural Estimator of Information for Time-Series Data with Dependency” has been accepted for publication in Entropy (DOI).
[2021/01/22] A new preprint, “Tighter expected generalization error bounds via Wasserstein distance”, is available in arXiv.
[2021/01/04] I joined Ericsson Research.
[2020/12/28] Our paper “Neural Estimators for Conditional Mutual Information Using Nearest Neighbors Sampling” has been accepted for publication in the IEEE Transactions on Signal Processing (DOI).
[2020/12/22] Our paper “On Random Subset Generalization Error Bounds and the Stochastic Gradient Langevin Dynamics Algorithm” (arXiv) has been accepted for presentation at the 2020 IEEE ITW.
[2020/11/24] A new preprint, “Causality Graph of Vehicular Traffic Flow”, is available in arXiv.
[2020/10/21] A new preprint, “On Random Subset Generalization Error Bounds and the Stochastic Gradient Langevin Dynamics Algorithm”, is available in arXiv.
[2020/06/15] A new preprint, “Neural Estimators for Conditional Mutual Information Using Nearest Neighbors Sampling”, is available in arXiv.
[2020/05/13] A new preprint, “Upper Bounds on the Generalization Error of Private Algorithms”, is available in arXiv.
[2020/01/24] Our article “Conditional Mutual Information Neural Estimator” has been accepted for presentation at the upcoming ICASSP 2020 in Barcelona, Spain. Check a preliminary version on arXiv.