72 citations · 310 across the 41 of their papers we have counts for
14 papers · 1 filter
Anchor PCA
Benedikt Seiter, Anya Fries, Julius von Kügelgen +1
Principal component analysis (PCA) is one of the most widely used unsupervised dimension reduction techniques. We study PCA for data from multiple related domains. Since principal…
Independent Mechanism Analysis and the Manifold Hypothesis
Shubhangi Ghosh, Luigi Gresele, Julius von Kügelgen +2
Independent Mechanism Analysis (IMA) seeks to address non-identifiability in nonlinear Independent Component Analysis (ICA) by assuming that the Jacobian of the mixing function has…
Nonparametric Identifiability of Causal Representations from Unknown Interventions
Julius von Kügelgen, Michel Besserve, Liang Wendong +5
We study causal representation learning, the task of inferring latent causal variables and their causal relations from high-dimensional mixtures of the variables. Prior work relies…
Causal Component Analysis
Liang Wendong, Armin Kekić, Julius von Kügelgen +4
Independent Component Analysis (ICA) aims to recover independent latent variables from observed mixtures thereof. Causal Representation Learning (CRL) aims instead to infer causall…
Probable Domain Generalization via Quantile Risk Minimization
Cian Eastwood, Alexander Robey, Shashank Singh +4
Domain generalization (DG) seeks predictors which perform well on unseen test distributions by leveraging data drawn from multiple related training distributions or domains. To ach…
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…
On Pitfalls of Identifiability in Unsupervised Learning. A Note on: "Desiderata for Representation Learning: A Causal Perspective"
Shubhangi Ghosh, Luigi Gresele, Julius von Kügelgen +2
Model identifiability is a desirable property in the context of unsupervised representation learning. In absence thereof, different models may be observationally indistinguishable…
Algorithmic Recourse in Partially and Fully Confounded Settings Through Bounding Counterfactual Effects
Julius von Kügelgen, Nikita Agarwal, Jakob Zeitler +2
Algorithmic recourse aims to provide actionable recommendations to individuals to obtain a more favourable outcome from an automated decision-making system. As it involves reasonin…
Independent mechanism analysis, a new concept?
Luigi Gresele, Julius von Kügelgen, Vincent Stimper +2
Independent component analysis provides a principled framework for unsupervised representation learning, with solid theory on the identifiability of the latent code that generated…
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 causal generative scene models via competition of experts
Julius von Kügelgen, Ivan Ustyuzhaninov, Peter Gehler +2
Learning how to model complex scenes in a modular way with recombinable components is a pre-requisite for higher-order reasoning and acting in the physical world. However, current…
Optimal experimental design via Bayesian optimization: active causal structure learning for Gaussian process networks
Julius von Kügelgen, Paul K Rubenstein, Bernhard Schölkopf +1
We study the problem of causal discovery through targeted interventions. Starting from few observational measurements, we follow a Bayesian active learning approach to perform thos…
Semi-Supervised Learning, Causality and the Conditional Cluster Assumption
Julius von Kügelgen, Alexander Mey, Marco Loog +1
While the success of semi-supervised learning (SSL) is still not fully understood, Schölkopf et al. (2012) have established a link to the principle of independent causal mechanisms…
Semi-Generative Modelling: Covariate-Shift Adaptation with Cause and Effect Features
Julius von Kügelgen, Alexander Mey, Marco Loog
Current methods for covariate-shift adaptation use unlabelled data to compute importance weights or domain-invariant features, while the final model is trained on labelled data onl…