Lars Kühmichel — accepted AI-conference papers

2026

JADAI: Jointly Amortizing Adaptive Design and Bayesian Inference

Niels Bracher, Lars Kühmichel, Desi Ivanova, Xavier Intes, Paul Buerkner, Stefan Radev

ICML 2026poster

We consider problems of parameter estimation where design variables can be actively optimized to maximize information gain. To this end, we introduce JADAI, a framework that jointly amortizes Bayesian adaptive design and inference by training a policy, a history network, and an inference network end…

Cited by 0 Source ↗Scholar ↗

2023

On the Convergence Rate of Gaussianization with Random Rotations

Felix Draxler, Lars Kühmichel, Armand Rousselot, Jens Müller, Christoph Schnoerr, Ullrich Koethe

ICML 2023poster

Gaussianization is a simple generative model that can be trained without backpropagation. It has shown compelling performance on low dimensional data. As the dimension increases, however, it has been observed that the convergence speed slows down. We show analytically that the number of required lay…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗