Selected Publications
See Google Scholar for a complete list.
See Google Scholar for a complete list.
Quantification of Distribution Shifts: Quantifying when models operate outside their training regime.
(divergence estimation, density ratios, out-of-distribution detection)
L. Gruber, M. Holzleitner, S. Hochreiter, and W. Zellinger, “Minimax-Optimal Aggregation for Density Ratio Estimation,” ICLR, 2026
C. Hofmann, Ch. Huber, B. Lehner, D. Klotz, S. Hochreiter, and W. Zellinger, “AP-OOD: Attention Pooling for Out-of- Distribution Detection,” ICLR 2026
W. Zellinger, “Binary losses for density ratio estimation,” ICLR, 2025 [link] [code]
W. Zellinger, S. Kindermann, and S. Pereverzyev, “Adaptive learning of density ratios in RKHS,” JMLR, 2023 [link]
Correction of Distribution Shifts: Adapting models to changing conditions.
(domain adaptation, few-shot learning, re-calibration methods)
M.-C. Dinu, M. Holzleitner, M. Beck, D.H. Nguyen, A. Huber, H. Eghbal-zadeh, B. Moser, S. Pereverzyev, S. Hochreiter, and W. Zellinger, “Addressing parameter choice issues in unsupervised domain adaptation by aggregation,” ICLR (oral), 2023 [link]
W. Zellinger, N. Shepeleva, M.-C. Dinu, H. Eghbal-zadeh, H.D. Nguyen, B. Nessler, S. Pereverzyev, and B. Moser, “The balancing principle for parameter choice in distance-regularized domain adaptation,” NeurIPS, 2021 [link]
W. Zellinger, T. Grubinger, E. Lughofer, T. Natschläger, S. Saminger-Platz, "Central moment discrepancy (CMD) for domain-invariant representation learning," ICLR, 2017 [link] [code]
Robustness Evaluation & Certification Readiness: Benchmarks and protocols for testing ML systems.
(benchmarks, evaluation protocols, safety & regulatory alignment)
P. Setinek, G. Galletti, T. Gross, D. Schnürer, J. Brandstetter, and W. Zellinger, “SIMSHIFT: A benchmark for adapting neural surrogates to distribution shifts,” preprint, 2025 [link]
L. Gruber, M. Holzleitner, J. Lehner, S. Hochreiter, and W. Zellinger, “Overcoming saturation in density ratio estimation by iterated regularization,” ICML, 2024 [link]
K. Schweighofer, B. Brune, L. Gruber, S. Schmid, A. Aufreiter, A. Gruber, T. Doms, S. Eder, F. Mayer, X.-P. Stadlbauer, C. Schwald, W. Zellinger, B. Nessler, and S. Hochreiter, “Safe and certifiable AI systems: Concepts, challenges, and lessons learned,” TÜV AUSTRIA Report (industry white paper), 2025 [link]