activity
20192021
most citedDisentangling the Gauss-Newton Method and Approximate Inference for Neural Networks

2 citations · 2 across the 3 of their papers we have counts for

collaborators
Showing stat.MLShow all

5 papers · 1 filter

stat.ML2021

Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning

Alexander Immer, Matthias Bauer, Vincent Fortuin +2

Marginal-likelihood based model-selection, even though promising, is rarely used in deep learning due to estimation difficulties. Instead, most approaches rely on validation data,…

stat.ML2020

Improving predictions of Bayesian neural nets via local linearization

Alexander Immer, Maciej Korzepa, Matthias Bauer

The generalized Gauss-Newton (GGN) approximation is often used to make practical Bayesian deep learning approaches scalable by replacing a second order derivative with a product of…

stat.ML20202 cited

Disentangling the Gauss-Newton Method and Approximate Inference for Neural Networks

Alexander Immer

In this thesis, we disentangle the generalized Gauss-Newton and approximate inference for Bayesian deep learning. The generalized Gauss-Newton method is an optimization method that…

stat.ML2020

Continual Deep Learning by Functional Regularisation of Memorable Past

Pingbo Pan, Siddharth Swaroop, Alexander Immer +3

Continually learning new skills is important for intelligent systems, yet standard deep learning methods suffer from catastrophic forgetting of the past. Recent works address this…

stat.ML2019

Approximate Inference Turns Deep Networks into Gaussian Processes

Mohammad Emtiyaz Khan, Alexander Immer, Ehsan Abedi +1

Deep neural networks (DNN) and Gaussian processes (GP) are two powerful models with several theoretical connections relating them, but the relationship between their training metho…