Researcher Shows Classic EM M-step Derivations Rest on Non-convex Problems

A researcher shows that M-step derivations for factor analysis, linear dynamical systems, and mixed factor analyzers are typically framed as non-convex optimization problems, and demonstrates that reformulating one as a convex problem keeps all derivations valid, raising questions about classic textbook treatments.

2026-11-09 ~ 2026-11-09 · 2 related posts

• EM's M-step derivations hide nonconvex optimization problems, researcher notes — caglar_ee · 2026-11-09
• Researcher shows EM M-step derivations for factor analysis can all be made convex — caglar_ee · 2026-11-09