9 citations · 11 across the 13 of their papers we have counts for
5 papers · 1 filter
The internal model principle in reservoir computing
Danyal Saqib, Alberto Padoan
The paper studies learning in reservoir computing systems through the lens of the internal model principle. The key idea is to model training signals as outputs of an exogenous sig…
Open Quadratic Optimization Programs
Alberto Padoan
The paper studies open optimization programs, that is, parametric optimization programs viewed as open systems, and their interconnection. Each open optimization program is assigne…
On Dominant Manifolds in Reservoir Computing Networks
Noa Kaplan, Alberto Padoan, Anastasia Bizyaeva
Understanding how training shapes the geometry of recurrent network dynamics is a central problem in time-series modeling. We study the emergence of low-dimensional dominant manifo…
Scaled Relative Graphs in Normed Spaces
Alberto Padoan
The paper extends the Scaled Relative Graph (SRG) framework of Ryu, Hannah, and Yin from Hilbert spaces to normed spaces. Our extension replaces the inner product with a regular pa…
From time series to dissipativity of linear systems with dynamic supply rates
Henk J. van Waarde, Jeremy Coulson, Alberto Padoan
This paper studies the problem of verifying dissipativity of linear time-invariant (LTI) systems using input-output data. We leverage behavioral systems theory to express dissipati…