1 citations · 1 across the 4 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
math.OC2026
Non-Euclidean Gradient Descent Has Many Edges of Stability
Peter Zaika, Zakhar Shumaylov
Recent observations that deep learning models train at the edge of stability have renewed interest in understanding stability properties of classical optimization algorithms. For q…
cs.LG2026
Muon is Not That Special: Random or Inverted Spectra Work Just as Well
Zakhar Shumaylov, Nathaël Da Costa, Peter Zaika +6
The recent empirical success of the Muon optimizer has renewed interest in non-Euclidean optimization, typically justified by similarities with second-order methods, and linear min…