2.1k citations · 5.7k across the 61 of their papers we have counts for
11 papers · 1 filter
Estimating Treatment Effects with Independent Component Analysis
Patrik Reizinger, Lester Mackey, Wieland Brendel +1
Independent Component Analysis (ICA) uses a measure of non-Gaussianity to identify latent sources from data and estimate their mixing coefficients (Shimizu et al., 2006). Meanwhile…
Position: Understanding LLMs Requires More Than Statistical Generalization
Patrik Reizinger, Szilvia Ujváry, Anna Mészáros +3
The last decade has seen blossoming research in deep learning theory attempting to answer, "Why does deep learning generalize?" A powerful shift in perspective precipitated this pr…
Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning
Patrik Reizinger, Siyuan Guo, Ferenc Huszár +2
Identifying latent representations or causal structures is important for good generalization and downstream task performance. However, both fields have been developed rather indepe…
Embrace the Gap: VAEs Perform Independent Mechanism Analysis
Patrik Reizinger, Luigi Gresele, Jack Brady +6
Variational autoencoders (VAEs) are a popular framework for modeling complex data distributions; they can be efficiently trained via variational inference by maximizing the evidenc…
Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style
Julius von Kügelgen, Yash Sharma, Luigi Gresele +4
Self-supervised representation learning has shown remarkable success in a number of domains. A common practice is to perform data augmentation via hand-crafted transformations inte…
Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding
David Klindt, Lukas Schott, Yash Sharma +4
We construct an unsupervised learning model that achieves nonlinear disentanglement of underlying factors of variation in naturalistic videos. Previous work suggests that represent…
Local Convolutions Cause an Implicit Bias towards High Frequency Adversarial Examples
Josue Ortega Caro, Yilong Ju, Ryan Pyle +4
Adversarial Attacks are still a significant challenge for neural networks. Recent work has shown that adversarial perturbations typically contain high-frequency features, but the r…
Accurate, reliable and fast robustness evaluation
Wieland Brendel, Jonas Rauber, Matthias Kümmerer +2
Throughout the past five years, the susceptibility of neural networks to minimal adversarial perturbations has moved from a peculiar phenomenon to a core issue in Deep Learning. De…
Trace your sources in large-scale data: one ring to find them all
Alexander Böttcher, Wieland Brendel, Bernhard Englitz +1
An important preprocessing step in most data analysis pipelines aims to extract a small set of sources that explain most of the data. Currently used algorithms for blind source sep…
Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models
Wieland Brendel, Jonas Rauber, Matthias Bethge
Many machine learning algorithms are vulnerable to almost imperceptible perturbations of their inputs. So far it was unclear how much risk adversarial perturbations carry for the s…
Comment on "Biologically inspired protection of deep networks from adversarial attacks"
Wieland Brendel, Matthias Bethge
A recent paper suggests that Deep Neural Networks can be protected from gradient-based adversarial perturbations by driving the network activations into a highly saturated regime.…