Johannes von Oswald

ETH Zürich
Johannes von Oswald
Institut für Theoretische Informatik
CAB J 21.2
Universitätstrasse 6
8092 Zürich

Phone: +41 44 632 26 76
E-Mail: voswaldj@ethz.ch

Research Interests

My research is focused on learning algorithms for neural networks to tackle problems with continuous and sparse data. Under these assumptions, the trade-off between model bias and sample efficiency lies at the heart of my interests in biological and artificial neural networks, statistical learning theory and reinforcement learning. In particular, during my PhD I am developing tools around a class of neural network architectures termed HyperNetworks that can incorporate model design and its optimization into a single framework.

I am gratefull for the support I receive from the Swiss Data Science Center.

Selected Publications

Learning where to learn: Gradient sparsity in meta and continual learning
(joint work with Dominic Zhao, Seijin Kobayashi, Simon Schug, Massimo Caccia, Nicolas Zucchet and João Sacramento)
35th Conference on Neural Information Processing Systems (NeurIPS 2021), 2021.

On the reversed bias-variance tradeoff in deep ensembles
(joint work with Seijin Kobayashi and Benjamin Grewe)
ICML 2021 Workshop on Uncertainty and Robustness in Deep Learning, 2021

Neural networks with late-phase weights
(joint work with Seijin Kobayashi, Benjamin Grewe and João Sacramento)
International Conference on Learning Representations, 2021

A contrastive rule for meta-learning
(joint work with Nicolas Zucchet, Simon Schug, Dominic Zhao and João Sacramento)
arXiv preprint, 2021

Continual learning with hypernetworks
(joint work with Christian Henning, Benjamin Grewe and João Sacramento)
International Conference on Learning Representations, 2020

Meta-learning via hypernetworks
(joint work with Dominic Zhao, Seijin Kobayashi, João Sacramento)
NeurIPS Workshop on Meta-Learning , 2020


Check Google scholar for an updated and complete publication history.