Alexander Immer
Alexander Immer
PhD student, ETH Zürich, Max Planck Institute for Intelligent Systems
Bestätigte E-Mail-Adresse bei - Startseite
Zitiert von
Zitiert von
Approximate inference turns deep networks into gaussian processes
ME Khan, A Immer, E Abedi, M Korzepa
NeurIPS 2019, 2019
Continual deep learning by functional regularisation of memorable past
P Pan, S Swaroop, A Immer, R Eschenhagen, RE Turner, ME Khan
NeurIPS 2020, 2020
Scalable marginal likelihood estimation for model selection in deep learning
A Immer, M Bauer, V Fortuin, G Rätsch, ME Khan
ICML 2021, 2021
Improving predictions of Bayesian neural nets via local linearization
A Immer, M Korzepa, M Bauer
AISTATS 2021, 703-711, 2021
Laplace Redux--Effortless Bayesian Deep Learning
E Daxberger, A Kristiadi, A Immer, R Eschenhagen, M Bauer, P Hennig
NeurIPS 2021, 2021
Optimizing routes of public transportation systems by analyzing the data of taxi rides
K Richly, R Teusner, A Immer, F Windheuser, L Wolf
Proceedings of the 1st International ACM SIGSPATIAL Workshop on Smart Cities …, 2015
Sub-Matrix Factorization for Real-Time Vote Prediction
A Immer, V Kristof, M Grossglauser, P Thiran
KDD 2020, 2280-2290, 2020
Probing as Quantifying the Inductive Bias of Pre-trained Representations
A Immer, LT Hennigen, V Fortuin, R Cotterell
ACL 2022, 2021
Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximations
A Immer, TFA van der Ouderaa, V Fortuin, G Rätsch, M van der Wilk
arXiv preprint arXiv:2202.10638, 2022
Pathologies in priors and inference for Bayesian transformers
T Cinquin, A Immer, M Horn, V Fortuin
AABI 2022, 2021
Disentangling the Gauss-Newton Method and Approximate Inference for Neural Networks
A Immer
École polytechnique fédérale de Lausanne (EPFL), 2020
Variational Inference with Numerical Derivatives: variance reduction through coupling
A Immer, GP Dehaene
arXiv preprint arXiv:1906.06914, 2019
Efficient learning of smooth probability functions from Bernoulli tests with guarantees
P Rolland, A Kavis, A Immer, A Singla, V Cevher
ICML 2019, 5459-5467, 2019
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–13