Lederer, Johannes

13 publications

WACV 2025 AnomalyDINO: Boosting Patch-Based Few-Shot Anomaly Detection with DINOv2 Simon Damm, Mike Laszkiewicz, Johannes Lederer, Asja Fischer
TMLR 2025 Cardinality Sparsity: Applications in Matrix-Matrix Multiplications and Machine Learning Ali Mohaddes, Johannes Lederer
ICLR 2025 How Many Samples Are Needed to Train a Deep Neural Network? Pegah Golestaneh, Mahsa Taheri, Johannes Lederer
TMLR 2025 Statistical Guarantees for Approximate Stationary Points of Shallow Neural Networks Mahsa Taheri, Fang Xie, Johannes Lederer
ICML 2024 Single-Model Attribution of Generative Models Through Final-Layer Inversion Mike Laszkiewicz, Jonas Ricker, Johannes Lederer, Asja Fischer
ICML 2022 Marginal Tail-Adaptive Normalizing Flows Mike Laszkiewicz, Johannes Lederer, Asja Fischer
AISTATS 2021 False Discovery Rates in Biological Networks Lu Yu, Tobias Kaufmann, Johannes Lederer
AISTATS 2021 Thresholded Adaptive Validation: Tuning the Graphical Lasso for Graph Recovery Mike Laszkiewicz, Asja Fischer, Johannes Lederer
ICMLW 2021 Copula-Based Normalizing Flows Mike Laszkiewicz, Johannes Lederer, Asja Fischer
JMLR 2021 Estimating the Lasso's Effective Noise Johannes Lederer, Michael Vogt
JMLR 2016 A Practical Scheme and Fast Algorithm to Tune the Lasso with Optimality Guarantees Michael Chichignoud, Johannes Lederer, Martin J. Wainwright
AAAI 2015 Compute Less to Get More: Using ORC to Improve Sparse Filtering Johannes Lederer, Sergio Guadarrama
AAAI 2015 Don't Fall for Tuning Parameters: Tuning-Free Variable Selection in High Dimensions with the TREX Johannes Lederer, Christian L. Müller