45 citations · 45 across the 6 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
The Spectral Dynamics and Noise Geometry of Muon
Pierfrancesco Beneventano, Mahmoud Abdelmoneum, Tomaso Poggio
Muon replaces a matrix gradient by its polar factor . This keeps the singular directions selected by the gradient, but makes the update spectrum flat. We stud…
cs.LG2017★ 45 cited
Theory II: Landscape of the Empirical Risk in Deep Learning
Qianli Liao, Tomaso Poggio
Previous theoretical work on deep learning and neural network optimization tend to focus on avoiding saddle points and local minima. However, the practical observation is that, at…