Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Morsbach, Felix"'
Research on the effects of essential hyperparameters of DP-SGD lacks consensus, verification, and replication. Contradictory and anecdotal statements on their influence make matters worse. While DP-SGD is the standard optimization algorithm for priva
Externí odkaz:
http://arxiv.org/abs/2411.02051
Autor:
Hasebrook, Niklas, Morsbach, Felix, Kannengießer, Niclas, Zöller, Marc, Franke, Jörg, Lindauer, Marius, Hutter, Frank, Sunyaev, Ali
Advanced programmatic hyperparameter optimization (HPO) methods, such as Bayesian optimization, have high sample efficiency in reproducibly finding optimal hyperparameter values of machine learning (ML) models. Yet, ML practitioners often apply less
Externí odkaz:
http://arxiv.org/abs/2203.01717
One barrier to more widespread adoption of differentially private neural networks is the entailed accuracy loss. To address this issue, the relationship between neural network architectures and model accuracy under differential privacy constraints ne
Externí odkaz:
http://arxiv.org/abs/2111.14924
Autor:
Hasebrook, Niklas, Morsbach, Felix, Kannengießer, Niclas, Franke, Jörg, Hutter, Frank, Sunyaev, Ali
Current advanced hyperparameter optimization (HPO) methods, such as Bayesian optimization, have high sampling efficiency and facilitate replicability. Nonetheless, machine learning (ML) practitioners (e.g., engineers, scientists) mostly apply less ad
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::939dd3b9e0b68a192a8a2d1b9e31fe49
This book gathers contributions to the 21st biannual symposium of the German Aerospace Aerodynamics Association (STAB) and the German Society for Aeronautics and Astronautics (DGLR). The individual chapters reflect ongoing research conducted by the S