Patrik Reizinger

According to our database, Patrik Reizinger authored at least 26 papers between 2019 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Who Guards the Guardians? The Challenges of Evaluating Identifiability of Learned Representations.

Shruti Joshi, Théo Saulus, Wieland Brendel, Philippe Brouillard, Dhanya Sridhar, Patrik Reizinger

CoRR, February, 2026

Causality is Key for Interpretability Claims to Generalise.

Shruti Joshi, Aaron Mueller, David A. Klindt, Wieland Brendel, Patrik Reizinger, Dhanya Sridhar

CoRR, February, 2026

2025

From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?

Aaron Mueller, Andrew Lee, Shruti Joshi, Ekdeep Singh Lubana, Dhanya Sridhar, Patrik Reizinger

CoRR, December, 2025

Out-of-distribution Tests Reveal Compositionality in Chess Transformers.

Anna Mészáros, Patrik Reizinger, Ferenc Huszár

CoRR, October, 2025

Estimating Treatment Effects with Independent Component Analysis.

Patrik Reizinger, Lester Mackey, Wieland Brendel, Rahul Krishnan

CoRR, July, 2025

Skill Learning via Policy Diversity Yields Identifiable Representations for Reinforcement Learning.

Patrik Reizinger, Bálint Mucsányi, Siyuan Guo, Benjamin Eysenbach, Bernhard Schölkopf, Wieland Brendel

CoRR, July, 2025

An Empirically Grounded Identifiability Theory Will Accelerate Self-Supervised Learning Research.

Patrik Reizinger, Randall Balestriero, David A. Klindt, Wieland Brendel

CoRR, April, 2025

From superposition to sparse codes: interpretable representations in neural networks.

David A. Klindt, Charles O'Neill, Patrik Reizinger, Harald Maurer, Nina Miolane

CoRR, March, 2025

Occam's Razor for SSL: Memory-Efficient Parametric Instance Discrimination.

Eric Gan, Patrik Reizinger, Alice Bizeul, Attila Juhos, Mark Ibrahim, Randall Balestriero, David A. Klindt, Wieland Brendel, Baharan Mirzasoleiman

Trans. Mach. Learn. Res., 2025

Position: An Empirically Grounded Identifiability Theory Will Accelerate Self Supervised Learning Research.

Patrik Reizinger, Randall Balestriero, David A. Klindt, Wieland Brendel

Proceedings of the Forty-second International Conference on Machine Learning, 2025

Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning.

Patrik Reizinger, Siyuan Guo, Ferenc Huszár, Bernhard Schölkopf, Wieland Brendel

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Cross-Entropy Is All You Need To Invert the Data Generating Process.

Patrik Reizinger, Alice Bizeul, Attila Juhos, Julia E. Vogt, Randall Balestriero, Wieland Brendel, David A. Klindt

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

InfoNCE: Identifying the Gap Between Theory and Practice.

Evgenia Rusak, Patrik Reizinger, Attila Juhos, Oliver Bringmann, Roland S. Zimmermann, Wieland Brendel

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2025

2024

Rule Extrapolation in Language Models: A Study of Compositional Generalization on OOD Prompts.

Anna Mészáros, Szilvia Ujváry, Wieland Brendel, Patrik Reizinger, Ferenc Huszár

CoRR, 2024

Understanding LLMs Requires More Than Statistical Generalization.

Patrik Reizinger, Szilvia Ujváry, Anna Mészáros, Anna Kerekes, Wieland Brendel, Ferenc Huszár

CoRR, 2024

Rule Extrapolation in Language Modeling: A Study of Compositional Generalization on OOD Prompts.

Anna Mészáros, Szilvia Ujváry, Wieland Brendel, Patrik Reizinger, Ferenc Huszar

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

Position: Understanding LLMs Requires More Than Statistical Generalization.

Patrik Reizinger, Szilvia Ujváry, Anna Mészáros, Anna Kerekes, Wieland Brendel, Ferenc Huszár

Proceedings of the Forty-first International Conference on Machine Learning, 2024

An Interventional Perspective on Identifiability in Gaussian LTI Systems with Independent Component Analysis.

Goutham Rajendran, Patrik Reizinger, Wieland Brendel, Pradeep Kumar Ravikumar

Proceedings of the Causal Learning and Reasoning, 2024

2023

nl-causal-representations.

Patrik Reizinger, Yash Sharma, Matthias Bethge, Bernhard Schölkopf, Ferenc Huszár, Wieland Brendel

Dataset, April, 2023

Jacobian-based Causal Discovery with Nonlinear ICA.

Patrik Reizinger, Yash Sharma, Matthias Bethge, Bernhard Schölkopf, Ferenc Huszár, Wieland Brendel

Trans. Mach. Learn. Res., 2023

2022

nl-causal-representations.

Patrik Reizinger, Yash Sharma, Matthias Bethge, Bernhard Schölkopf, Ferenc Huszár, Wieland Brendel

Dataset, August, 2022

ima-vae.

Patrik Reizinger, Luigi Gresele, Jack Brady, Dominik Zietlow, Julius von Kügelgen, Michel Besserve, Georg Martius, Wieland Brendel, Bernhard Schölkopf

Dataset, June, 2022

Embrace the Gap: VAEs Perform Independent Mechanism Analysis.

Patrik Reizinger, Luigi Gresele, Jack Brady, Julius von Kügelgen, Dominik Zietlow, Bernhard Schölkopf, Georg Martius, Wieland Brendel, Michel Besserve

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

2021

Handling Realistic Noise in Multi-Agent Systems with Self-Supervised Learning and Curiosity.

Márton Szemenyei, Patrik Reizinger

J. Artif. Intell. Soft Comput. Res., 2021

2020

Attention-Based Curiosity-Driven Exploration in Deep Reinforcement Learning.

Patrik Reizinger, Márton Szemenyei

Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

2019

Stochastic Weight Matrix-Based Regularization Methods for Deep Neural Networks.

Patrik Reizinger, Bálint Gyires-Tóth

Proceedings of the Machine Learning, Optimization, and Data Science, 2019