4 papers
Convergence of the EM algorithm via proximal techniques
Dominikus Noll
We investigate convergence of the expectation maximization algorithm by representing it as a generalized proximal method. Convergence of iterates and not just in value is investiga…
Minimizing transients via the Kreiss system norm
Pierre Apkarian, Dominikus Noll
We introduce system norms which assess transient behavior of stable Linear Time-Invariant (LTI) systems. This allows us to address undesired responses to initial conditions, finite…
Alternating Bregman projections and convergence of the EM algorithm
Dominikus Noll
We investigate convergence of alternating Bregman projections between non-convex sets and prove convergence to a point in the intersection, or to points realizing a gap between the…
Linear programming for finite-horizon vector-valued Markov decision processes
Anas Mifrani, Dominikus Noll
We propose a vector linear programming formulation for a non-stationary, finite-horizon Markov decision process with vector-valued rewards. Pareto efficient policies are shown to c…