%0 Generic %1 kumar2024mitigating %A Kumar, Mohit %A Moser, Bernhard A. %A Fischer, Lukas %D 2024 %K deep-learning mappings neural-networks %R https://arxiv.org/abs/2304.01300 %T On Mitigating the Utility-Loss in Differentially Private Learning: A new Perspective by a Geometrically Inspired Kernel Approach %U https://arxiv.org/pdf/2304.01300

@misc{kumar2024mitigating, added-at = {2024-01-23T19:25:22.000+0100}, archiveprefix = {arXiv}, author = {Kumar, Mohit and Moser, Bernhard A. and Fischer, Lukas}, biburl = {https://www.bibsonomy.org/bibtex/2081fadc878502efd174f49441fde406c/scch}, doi = {https://arxiv.org/abs/2304.01300}, eprint = {2304.01300}, interhash = {4fadbbfb24a634ce9a3b8897b7a4e3bc}, intrahash = {081fadc878502efd174f49441fde406c}, keywords = {deep-learning mappings neural-networks}, primaryclass = {cs.LG}, timestamp = {2024-01-23T19:25:22.000+0100}, title = {On Mitigating the Utility-Loss in Differentially Private Learning: A new Perspective by a Geometrically Inspired Kernel Approach}, url = {https://arxiv.org/pdf/2304.01300}, year = 2024 }