Why Local Minima Are Rare in High-Dimensional Random Landscapes

N/A

Why Local Minima Are Rare in High-Dimensional Landscapes A note on Hessians, saddles, and Morse critical points Grant Stenger May 17, 2025 Abstract A common slogan in high-dimensional optimization is that local minima are rare while saddle points are abundant. This slogan is not literally true for every smooth function: convex functions, for example, may have a unique global minimum and no saddles at all. A…

saved by

• Carmen Gutierrez

related reading

• Why Momentum Really Worksdistill.pub
• [1605.08101] Global rates of convergence for nonconvex optimization on manifoldsarxiv.org
• survey.dvimath.uchicago.edu
• notes.pdfjingbol.web.illinois.edu
• Dynamical Approach to RMT.pdfpeople.math.harvard.edu
• 1412.0233arxiv.org
• Hessian matrix - Wikipediaen.wikipedia.org
• [2605.15522] Stochastic Non-Smooth Convex Optimization with Unbounded Gradientsarxiv.org
• random matrices.dviwww-math.mit.edu
• Advanced stochastic analysishairer.org
• An Introduction to Malliavin Calculusuni-ulm.de
• Geometry of random sections of isotropic convex bodiesarxiv.org