Gradient-Weight Alignment as a Train-Time Proxy for Generalization in Classification Tasks

Item #:

085713-1784

Details

DOI: https://doi.org/10.52202/085713-1784
Author(s): Florian Hölzl, Daniel Rueckert, Georgios Kaissis
Pages: 59547-59574 (28 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 38
Date/Location: Held 2-7 December 2025, San Diego, California, USA and 30 November - 5 December 2025, Mexico City, Mexico.
Series: Advances in Neural Information Processing Systems 38
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)

DOI: https://doi.org/10.52202/085713-1784
Author(s): Florian Hölzl, Daniel Rueckert, Georgios Kaissis
Pages: 59547-59574 (28 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 38
Date/Location: Held 2-7 December 2025, San Diego, California, USA and 30 November - 5 December 2025, Mexico City, Mexico.
Series: Advances in Neural Information Processing Systems 38
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)