2 papers
cs.LG2023
Efficient Cross-Domain Federated Learning by MixStyle Approximation
Manuel Röder, Leon Heller, Maximilian Münch +1
With the advent of interconnected and sensor-equipped edge devices, Federated Learning (FL) has gained significant attention, enabling decentralized learning while maintaining data…
cs.LG2022
Revisiting Memory Efficient Kernel Approximation: An Indefinite Learning Perspective
Simon Heilig, Maximilian Münch, Frank-Michael Schleif
Matrix approximations are a key element in large-scale algebraic machine learning approaches. The recently proposed method MEKA (Si et al., 2014) effectively employs two common ass…