research
∙
07/05/2023
From NeurODEs to AutoencODEs: a mean-field control framework for width-varying Neural Networks
In our work, we build upon the established connection between Residual N...
share
research
∙
02/23/2023
A subgradient method with constant step-size for ℓ_1-composite optimization
Subgradient methods are the natural extension to the non-smooth case of ...
research
∙
09/08/2022
Losing momentum in continuous-time stochastic optimisation
The training of deep neural networks and other modern machine learning m...
research
∙
10/24/2021