216 citations · 689 across the 90 of their papers we have counts for
95 papers
Discrete-time polynomial systems with inputs and outputs: structure, reachability, observability, and minimal realizations
Eduardo D. Sontag
We study the realization problem for discrete-time input/output polynomial systems. These are formalized using tools from commutative algebra and algebraic geometry as systems whos…
On the ISS Property of the Gradient Flow for Single Hidden-Layer Neural Networks with Linear Activations
Arthur Castello B. de Oliveira, Milad Siami, Eduardo D. Sontag
Recent research in neural networks and machine learning suggests that using many more parameters than strictly required by the initial complexity of a regression problem can result…
An observability result related to active sensing
Eduardo D. Sontag, Debojyoti Biswas, Noah J. Cowan
For a general class of translationally invariant systems with a specific category of nonlinearity in the output, this paper presents necessary and sufficient conditions for global…
Remarks on input to state stability of perturbed gradient flows, motivated by model-free feedback control learning
Eduardo D. Sontag
Recent work on data-driven control and reinforcement learning has renewed interest in a relative old field in control theory: model-free optimal control approaches which work direc…
Long-term regulation of prolonged epidemic outbreaks in large populations via adaptive control: a singular perturbation approach
M. Ali Al-Radhawi, Mahdiar Sadeghi, Eduardo D. Sontag
Initial hopes of quickly eradicating the COVID-19 pandemic proved futile, and the goal shifted to controlling the peak of the infection, so as to minimize the load on healthcare sy…
Learning Recurrent Neural Net Models of Nonlinear Systems
Joshua Hanson, Maxim Raginsky, Eduardo Sontag
We consider the following learning problem: Given sample pairs of input and output signals generated by an unknown nonlinear system (which is not assumed to be causal or time-invar…