Dr. Jan Poland
Jan Poland, Ph.D. is Principle Scientist at Corporate Research,
ABB
Switzerland Ltd.
His research interests include:
theory of machine learning, active learning,
function minimization, reinforcement learning,
algorithmic information theory, decision theory, control theory, and
control of complex systems.
Jan coauthored
The critical spectrum of a strongly continuous semigroup,
New methods for spectral clustering,
Adaptive online prediction by following the perturbed leader,
Prediction with expert advice by following the perturbed leader for
general weights,
Amplifying the block matrix structure for spectral
clustering,
Convergence of discrete MDL for sequential prediction,
On the convergence speed of MDL predictions for Bernoulli
sequences,
Main vector adaptation: A CMA variant with linear time and space
complexity,
Defensive universal learning with experts, and
Universal learning of repeated matrix games.
Read the
full list of his publications!
Jan earned his Ph.D. at the
University of Tübingen, Germany with the thesis
Modellgestützte und Evolutionäre Optimierungsverfahren
für
die
Motorentwicklung and his Master’s at the University of
Tübingen,
Germany with
the thesis
“Der Spektrale Abbildungssatz für Operatorhalbgruppen und das
Kritische
Spektrum”. He did his post-doc at Lugano and Sapporo.
