To estimate the parameters of the Gaussian mixture model (GMM), the popular solution is to use the Expectation maximization (EM) algorithm. However, the estimated parameters for GMM using the EM can easily get into the local minimum. The graduated non-convexity is one of the popular solutions for solving the non-convexity problems. Can we use the graduated non-convexity to estimate the parameters of GMM?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.