Gradient EM converges exponentially to optimal population loss minimizers for agnostic fitting of k parametric functions under strong convexity and smoothness of the loss, proper initialization, and separation conditions.
Phase retrieval using alternating minimization.IEEE Transactions on Signal Processing, 63(18):4814–4826
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
A new weighted Riemannian gradient descent (WRGD) algorithm with a custom metric on rank-1 matrices enables nearly isometric embedding and linear convergence with small factor for generalized phase retrieval from Gaussian measurements.
citing papers explorer
-
Expectation Maximization (EM) Converges for General Agnostic Mixtures
Gradient EM converges exponentially to optimal population loss minimizers for agnostic fitting of k parametric functions under strong convexity and smoothness of the loss, proper initialization, and separation conditions.
-
Weighted Riemannian Optimization for Solving Quadratic Equations from Gaussian Magnitude Measurements
A new weighted Riemannian gradient descent (WRGD) algorithm with a custom metric on rank-1 matrices enables nearly isometric embedding and linear convergence with small factor for generalized phase retrieval from Gaussian measurements.