works on
ai risk 1organizational dynamics 1responsible ai 1risk perception 1sociotechnical systems 1system safety 1

From the 1 of 2 papers with an AI index.

researchers with a paper here
collaborating institutions
Showing math.OCShow all

1 paper · 1 filter

math.OC2026

Saddle Point Evasion via Curvature-Regularized Gradient Dynamics

Liraz Mudrik, Isaac Kaminer, Sean Kragelund +1

Nonconvex optimization underlies many modern machine learning and control tasks, where saddle points pose the dominant obstacle to reliable convergence in high-dimensional settings…