3 papers
math.OC2026
Gray-Box Optimization using Optimism in the Face of Uncertainty
Katrin Baumgärtner, Léo Simpson, Moritz Diehl
This paper considers sequential gray-box optimization where the objective function is given as the composition of a loss function and a parametric model. Crucially, the parameters…
eess.SY2026
Identification of a Kalman filter: consistency of local solutions
Léo Simpson, Moritz Diehl
Prediction error and maximum likelihood methods are powerful tools for identifying linear dynamical systems and, in particular, enable the joint estimation of model parameters and…
math.ST2026
Finite-sample bounds for multi-output system identification
Léo Simpson, Katrin Baumgärtner, Johannes Köhler +1
This paper presents uniform-in-time finite-sample bounds for regularized linear regression with vector-valued outputs and conditionally zero-mean subgaussian noise. By revisiting c…