On permutation symmetries in Bayesian neural network posteriors: a variational perspective
The elusive nature of gradient-based optimization in neural networks is tied to their loss
landscape geometry, which is poorly understood. However recent work has brought solid …
landscape geometry, which is poorly understood. However recent work has brought solid …
Improving Scalability and Inference in Probabilistic Deep Models
S Rossi - 2022 - theses.hal.science
Throughout the last decade, deep learning has reached a sufficient level of maturity to
become the preferred choice to solve machine learning-related problems or to aid decision …
become the preferred choice to solve machine learning-related problems or to aid decision …
[PDF][PDF] Extended Curriculum Vitae
P Michiardi - michiard.eurecom.io
Extended Curriculum Vitae Page 1 Extended Curriculum Vitae Prof. Pietro Michiardi, Ph.D.
Appointments 2019 – now Full Professor, EURECOM, France 2016 – now Director of the Data …
Appointments 2019 – now Full Professor, EURECOM, France 2016 – now Director of the Data …