Patrik Reizinger

Publication Activity (10 Years)

Years Active: 2019-2024
Publications (10 Years): 13

Top Topics

Causal Discovery

Independent Component Analysis

Source Separation

Top Venues

Publications

Goutham Rajendran, Patrik Reizinger, Wieland Brendel, Pradeep Kumar Ravikumar
An Interventional Perspective on Identifiability in Gaussian LTI Systems with Independent Component Analysis. CLeaR (2024)
Patrik Reizinger, Szilvia Ujváry, Anna Mészáros, Anna Kerekes, Wieland Brendel, Ferenc Huszár
Understanding LLMs Requires More Than Statistical Generalization. CoRR (2024)
Evgenia Rusak, Patrik Reizinger, Attila Juhos, Oliver Bringmann, Roland S. Zimmermann, Wieland Brendel
InfoNCE: Identifying the Gap Between Theory and Practice. CoRR (2024)
Patrik Reizinger, Siyuan Guo, Ferenc Huszár, Bernhard Schölkopf, Wieland Brendel
Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning. CoRR (2024)
Patrik Reizinger, Yash Sharma, Matthias Bethge, Bernhard Schölkopf, Ferenc Huszár, Wieland Brendel
Jacobian-based Causal Discovery with Nonlinear ICA. Trans. Mach. Learn. Res. 2023 (2023)
Goutham Rajendran, Patrik Reizinger, Wieland Brendel, Pradeep Ravikumar
An Interventional Perspective on Identifiability in Gaussian LTI Systems with Independent Component Analysis. CoRR (2023)
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)
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)
Márton Szemenyei, Patrik Reizinger
Handling Realistic Noise in Multi-Agent Systems with Self-Supervised Learning and Curiosity. J. Artif. Intell. Soft Comput. Res. 12 (2) (2021)
Patrik Reizinger, Márton Szemenyei
Attention-Based Curiosity-Driven Exploration in Deep Reinforcement Learning. ICASSP (2020)
Patrik Reizinger, Bálint Gyires-Tóth
Stochastic Weight Matrix-Based Regularization Methods for Deep Neural Networks. LOD (2019)
Patrik Reizinger, Bálint Gyires-Tóth
Stochastic Weight Matrix-based Regularization Methods for Deep Neural Networks. CoRR (2019)
Patrik Reizinger, Márton Szemenyei
Attention-based Curiosity-driven Exploration in Deep Reinforcement Learning. CoRR (2019)