#machine learning
Jan 2025
Sublinear Variational Optimization of Gaussian Mixture Models with Millions to Billions of Parameters
The effectiveness of large-scale GMMs on the task of zero-shot image denoising, where sublinear training results in state-of-the-art denoising times while competitive denoising performance is maintained, is demonstrated.
S. Salwig, Till Kahlke, F. Hirschberger et al.
· arXiv.org · 1 citation