Julius von Kügelgen

Publication Activity (10 Years)

Years Active: 2018-2024
Publications (10 Years): 64

Top Topics

Partial Observability

Supervised Learning

Causal Inference

Top Venues

Publications

Julius von Kügelgen
Identifiable Causal Representation Learning: Unsupervised, Multi-View, and Multi-Environment. CoRR (2024)
Dingling Yao, Danru Xu, Sébastien Lachapelle, Sara Magliacane, Perouz Taslakian, Georg Martius, Julius von Kügelgen, Francesco Locatello
Multi-View Causal Representation Learning with Partial Observability. ICLR (2024)
Klaus-Rudolf Kladny, Julius von Kügelgen, Bernhard Schölkopf, Michael Muehlebach
Deep Backtracking Counterfactuals for Causally Compliant Explanations. Trans. Mach. Learn. Res. 2024 (2024)
Danru Xu, Dingling Yao, Sébastien Lachapelle, Perouz Taslakian, Julius von Kügelgen, Francesco Locatello, Sara Magliacane
A Sparsity Principle for Partially Observable Causal Representation Learning. CoRR (2024)
Dingling Yao, Danru Xu, Sébastien Lachapelle, Sara Magliacane, Perouz Taslakian, Georg Martius, Julius von Kügelgen, Francesco Locatello
Multi-View Causal Representation Learning with Partial Observability. CoRR (2023)
Cian Eastwood, Shashank Singh, Andrei Liviu Nicolicioiu, Marin Vlastelica Pogancic, Julius von Kügelgen, Bernhard Schölkopf
Spuriosity Didn't Kill the Classifier: Using Invariant Predictions to Harness Spurious Features. NeurIPS (2023)
Klaus-Rudolf Kladny, Julius von Kügelgen, Bernhard Schölkopf, Michael Muehlebach
Causal effect estimation from observational and interventional data through matrix weighted linear estimators. UAI (2023)
Cian Eastwood, Andrei Liviu Nicolicioiu, Julius von Kügelgen, Armin Kekic, Frederik Träuble, Andrea Dittadi, Bernhard Schölkopf
DCI-ES: An Extended Disentanglement Framework with Connections to Identifiability. ICLR (2023)
Wendong Liang, Armin Kekic, Julius von Kügelgen, Simon Buchholz, Michel Besserve, Luigi Gresele, Bernhard Schölkopf
Causal Component Analysis. NeurIPS (2023)
Jack Brady, Roland S. Zimmermann, Yash Sharma, Bernhard Schölkopf, Julius von Kügelgen, Wieland Brendel
Provably Learning Object-Centric Representations. CoRR (2023)
Julius von Kügelgen, Michel Besserve, Wendong Liang, Luigi Gresele, Armin Kekic, Elias Bareinboim, David M. Blei, Bernhard Schölkopf
Nonparametric Identifiability of Causal Representations from Unknown Interventions. NeurIPS (2023)
Felix Laumann, Julius von Kügelgen, Junhyung Park, Bernhard Schölkopf, Mauricio Barahona
Kernel-Based Independence Tests for Causal Structure Learning on Functional Data. Entropy 25 (12) (2023)
Cian Eastwood, Shashank Singh, Andrei Liviu Nicolicioiu, Marin Vlastelica, Julius von Kügelgen, Bernhard Schölkopf
Spuriosity Didn't Kill the Classifier: Using Invariant Predictions to Harness Spurious Features. CoRR (2023)
Jack Brady, Roland S. Zimmermann, Yash Sharma, Bernhard Schölkopf, Julius von Kügelgen, Wieland Brendel
Provably Learning Object-Centric Representations. ICML (2023)
Julius von Kügelgen, Abdirisak Mohamed, Sander Beckers
Backtracking Counterfactuals. CLeaR (2023)
Matthias Tangemann, Steffen Schneider, Julius von Kügelgen, Francesco Locatello, Peter Vincent Gehler, Thomas Brox, Matthias Kümmerer, Matthias Bethge, Bernhard Schölkopf
Unsupervised Object Learning via Common Fate. CLeaR (2023)
Klaus-Rudolf Kladny, Julius von Kügelgen, Bernhard Schölkopf, Michael Muehlebach
Deep Backtracking Counterfactuals for Causally Compliant Explanations. CoRR (2023)
Julius von Kügelgen, Michel Besserve, Wendong Liang, Luigi Gresele, Armin Kekic, Elias Bareinboim, David M. Blei, Bernhard Schölkopf
Nonparametric Identifiability of Causal Representations from Unknown Interventions. CoRR (2023)
Klaus-Rudolf Kladny, Julius von Kügelgen, Bernhard Schölkopf, Michael Muehlebach
Causal Effect Estimation from Observational and Interventional Data Through Matrix Weighted Linear Estimators. CoRR (2023)
Shubhangi Ghosh, Luigi Gresele, Julius von Kügelgen, Michel Besserve, Bernhard Schölkopf
Independent Mechanism Analysis and the Manifold Hypothesis. CoRR (2023)
Armin Kekic, Jonas Dehning, Luigi Gresele, Julius von Kügelgen, Viola Priesemann, Bernhard Schölkopf
Evaluating vaccine allocation strategies using simulation-assisted causal modeling. Patterns 4 (6) (2023)
Wendong Liang, Armin Kekic, Julius von Kügelgen, Simon Buchholz, Michel Besserve, Luigi Gresele, Bernhard Schölkopf
Causal Component Analysis. CoRR (2023)
Cian Eastwood, Julius von Kügelgen, Linus Ericsson, Diane Bouchacourt, Pascal Vincent, Bernhard Schölkopf, Mark Ibrahim
Self-Supervised Disentanglement by Leveraging Structure in Data Augmentations. CoRR (2023)
Christian Toth, Lars Lorch, Christian Knoll, Andreas Krause, Franz Pernkopf, Robert Peharz, Julius von Kügelgen
Active Bayesian Causal Inference. CoRR (2022)
Julius von Kügelgen, Amir-Hossein Karimi, Umang Bhatt, Isabel Valera, Adrian Weller, Bernhard Schölkopf
On the Fairness of Causal Algorithmic Recourse. AAAI (2022)
Shubhangi Ghosh, Luigi Gresele, Julius von Kügelgen, Michel Besserve, Bernhard Schölkopf
On Pitfalls of Identifiability in Unsupervised Learning. A Note on: "Desiderata for Representation Learning: A Causal Perspective". CoRR (2022)
Cian Eastwood, Alexander Robey, Shashank Singh, Julius von Kügelgen, Hamed Hassani, George J. Pappas, Bernhard Schölkopf
Probable Domain Generalization via Quantile Risk Minimization. NeurIPS (2022)
Cian Eastwood, Andrei Liviu Nicolicioiu, Julius von Kügelgen, Armin Kekic, Frederik Träuble, Andrea Dittadi, Bernhard Schölkopf
DCI-ES: An Extended Disentanglement Framework with Connections to Identifiability. CoRR (2022)
Ronan Perry, Julius von Kügelgen, Bernhard Schölkopf
Causal Discovery in Heterogeneous Environments Under the Sparse Mechanism Shift Hypothesis. NeurIPS (2022)
Patrik Reizinger, Luigi Gresele, Jack Brady, Julius von Kügelgen, Dominik Zietlow, Bernhard Schölkopf, Georg Martius, Wieland Brendel, Michel Besserve
Embrace the Gap: VAEs Perform Independent Mechanism Analysis. CoRR (2022)
Lukas Schott, Julius von Kügelgen, Frederik Träuble, Peter Vincent Gehler, Chris Russell, Matthias Bethge, Bernhard Schölkopf, Francesco Locatello, Wieland Brendel
Visual Representation Learning Does Not Generalize Strongly Within the Same Domain. ICLR (2022)
Christian Toth, Lars Lorch, Christian Knoll, Andreas Krause, Franz Pernkopf, Robert Peharz, Julius von Kügelgen
Active Bayesian Causal Inference. NeurIPS (2022)
Patrik Reizinger, Luigi Gresele, Jack Brady, Julius von Kügelgen, Dominik Zietlow, Bernhard Schölkopf, Georg Martius, Wieland Brendel, Michel Besserve
Embrace the Gap: VAEs Perform Independent Mechanism Analysis. NeurIPS (2022)
Armin Kekic, Jonas Dehning, Luigi Gresele, Julius von Kügelgen, Viola Priesemann, Bernhard Schölkopf
Evaluating vaccine allocation strategies using simulation-assisted causal modelling. CoRR (2022)
Bernhard Schölkopf, Julius von Kügelgen
From Statistical to Causal Learning. CoRR (2022)
Luigi Gresele, Julius von Kügelgen, Jonas M. Kübler, Elke Kirschbaum, Bernhard Schölkopf, Dominik Janzing
Causal Inference Through the Structural Causal Marginal Problem. CoRR (2022)
Cian Eastwood, Alexander Robey, Shashank Singh, Julius von Kügelgen, Hamed Hassani, George J. Pappas, Bernhard Schölkopf
Probable Domain Generalization via Quantile Risk Minimization. CoRR (2022)
Osama Makansi, Julius von Kügelgen, Francesco Locatello, Peter Vincent Gehler, Dominik Janzing, Thomas Brox, Bernhard Schölkopf
You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction. ICLR (2022)
Julius von Kügelgen, Abdirisak Mohamed, Sander Beckers
Backtracking Counterfactuals. CoRR (2022)
Luigi Gresele, Julius von Kügelgen, Jonas M. Kübler, Elke Kirschbaum, Bernhard Schölkopf, Dominik Janzing
Causal Inference Through the Structural Causal Marginal Problem. ICML (2022)
Ronan Perry, Julius von Kügelgen, Bernhard Schölkopf
Causal Discovery in Heterogeneous Environments Under the Sparse Mechanism Shift Hypothesis. CoRR (2022)
Zhijing Jin, Julius von Kügelgen, Jingwei Ni, Tejas Vaidhya, Ayush Kaushal, Mrinmaya Sachan, Bernhard Schölkopf
Causal Direction of Data Collection Matters: Implications of Causal and Anticausal Learning for NLP. EMNLP (1) (2021)
Lukas Schott, Julius von Kügelgen, Frederik Träuble, Peter V. Gehler, Chris Russell, Matthias Bethge, Bernhard Schölkopf, Francesco Locatello, Wieland Brendel
Visual Representation Learning Does Not Generalize Strongly Within the Same Domain. CoRR (2021)
Luigi Gresele, Julius von Kügelgen, Vincent Stimper, Bernhard Schölkopf, Michel Besserve
Independent mechanism analysis, a new concept? NeurIPS (2021)
Zhijing Jin, Julius von Kügelgen, Jingwei Ni, Tejas Vaidhya, Ayush Kaushal, Mrinmaya Sachan, Bernhard Schölkopf
Causal Direction of Data Collection Matters: Implications of Causal and Anticausal Learning for NLP. CoRR (2021)
Julius von Kügelgen, Yash Sharma, Luigi Gresele, Wieland Brendel, Bernhard Schölkopf, Michel Besserve, Francesco Locatello
Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style. CoRR (2021)
Frederik Träuble, Julius von Kügelgen, Matthäus Kleindessner, Francesco Locatello, Bernhard Schölkopf, Peter V. Gehler
Backward-Compatible Prediction Updates: A Probabilistic Approach. CoRR (2021)
Julius von Kügelgen, Nikita Agarwal, Jakob Zeitler, Afsaneh Mastouri, Bernhard Schölkopf
Algorithmic Recourse in Partially and Fully Confounded Settings Through Bounding Counterfactual Effects. CoRR (2021)
Luigi Gresele, Julius von Kügelgen, Vincent Stimper, Bernhard Schölkopf, Michel Besserve
Independent mechanism analysis, a new concept? CoRR (2021)
Frederik Träuble, Julius von Kügelgen, Matthäus Kleindessner, Francesco Locatello, Bernhard Schölkopf, Peter V. Gehler
Backward-Compatible Prediction Updates: A Probabilistic Approach. NeurIPS (2021)
Matthias Tangemann, Steffen Schneider, Julius von Kügelgen, Francesco Locatello, Peter V. Gehler, Thomas Brox, Matthias Kümmerer, Matthias Bethge, Bernhard Schölkopf
Unsupervised Object Learning via Common Fate. CoRR (2021)
Osama Makansi, Julius von Kügelgen, Francesco Locatello, Peter V. Gehler, Dominik Janzing, Thomas Brox, Bernhard Schölkopf
You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction. CoRR (2021)
Julius von Kügelgen, Luigi Gresele, Bernhard Schölkopf
Simpson's Paradox in COVID-19 Case Fatality Rates: A Mediation Analysis of Age-Related Causal Effects. IEEE Trans. Artif. Intell. 2 (1) (2021)
Julius von Kügelgen, Yash Sharma, Luigi Gresele, Wieland Brendel, Bernhard Schölkopf, Michel Besserve, Francesco Locatello
Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style. NeurIPS (2021)
François Bertaux, Julius von Kügelgen, Samuel Marguerat, Vahid Shahrezaei
A bacterial size law revealed by a coarse-grained model of cell physiology. PLoS Comput. Biol. 16 (9) (2020)
Julius von Kügelgen, Umang Bhatt, Amir-Hossein Karimi, Isabel Valera, Adrian Weller, Bernhard Schölkopf
On the Fairness of Causal Algorithmic Recourse. CoRR (2020)
Amir-Hossein Karimi, Julius von Kügelgen, Bernhard Schölkopf, Isabel Valera
Algorithmic recourse under imperfect causal knowledge: a probabilistic approach. CoRR (2020)
Julius von Kügelgen, Alexander Mey, Marco Loog, Bernhard Schölkopf
Semi-supervised learning, causality, and the conditional cluster assumption. UAI (2020)
Julius von Kügelgen, Ivan Ustyuzhaninov, Peter V. Gehler, Matthias Bethge, Bernhard Schölkopf
Towards causal generative scene models via competition of experts. CoRR (2020)
Amir-Hossein Karimi, Julius von Kügelgen, Bernhard Schölkopf, Isabel Valera
Towards Causal Algorithmic Recourse. xxAI@ICML (2020)
Julius von Kügelgen, Alexander Mey, Marco Loog
Semi-Generative Modelling: Covariate-Shift Adaptation with Cause and Effect Features. AISTATS (2019)
Julius von Kügelgen, Marco Loog, Alexander Mey, Bernhard Schölkopf
Semi-Supervised Learning, Causality and the Conditional Cluster Assumption. CoRR (2019)
Julius von Kügelgen, Paul K. Rubenstein, Bernhard Schölkopf, Adrian Weller
Optimal experimental design via Bayesian optimization: active causal structure learning for Gaussian process networks. CoRR (2019)
Julius von Kügelgen, Alexander Mey, Marco Loog
Semi-Generative Modelling: Domain Adaptation with Cause and Effect Features. CoRR (2018)