3 papers
math.ST2025
Model-free filtering in high dimensions via projection and score-based diffusions
Sören Christensen, Jan Kallsen, Claudia Strauch +1
We consider the problem of recovering a latent signal from its noisy observation . The unknown law of , and in particular its support , are ac…
stat.ML2024
Learning to steer with Brownian noise
Stefan Ankirchner, Sören Christensen, Jan Kallsen +2
This paper considers an ergodic version of the bounded velocity follower problem, assuming that the decision maker lacks knowledge of the underlying system parameters and must lear…
q-bio.NC2024
Is Learning in Biological Neural Networks based on Stochastic Gradient Descent? An analysis using stochastic processes
Sören Christensen, Jan Kallsen
In recent years, there has been an intense debate about how learning in biological neural networks (BNNs) differs from learning in artificial neural networks. It is often argued th…