2 papers
cs.LG2026
Generalization at the Edge of Stability
Mario Tuci, Caner Korkmaz, Umut ÅimÅekli +1
Training modern neural networks often relies on large learning rates, operating at the edge of stability, where the optimization dynamics exhibit oscillatory and chaotic behavior.…
cs.CV2026
Parallelised Differentiable Straightest Geodesics for 3D Meshes
Hippolyte Verninas, Caner Korkmaz, Stefanos Zafeiriou +2
Machine learning has been progressively generalised to operate within non-Euclidean domains, but geometrically accurate methods for learning on surfaces are still falling behind. T…