I'm using pLSA (Probabilistic Latent Semantic Analysis). I'm trying to estimate the best value for some parameters with a process of k-fold cross-validation.

I have noticed that the model fitting is strongly influenced by the initialization. In order to choose the "best" initialization i'm using the trivial method of multiple random initializations.

Does someone know if do it exist a better way?Or maybe some good practices?



Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.