How to solve the “out of memory” problem in Logistic Regression achieved by “glmfit”

I use “glmfit” to build Logistic Regression. But the training dataset is too huge. I cannot load all the data into memory. Is there any method to build Logistic Regression in Matlab using batch learning? In other words, it can load the training data gradually when training the model.

Thank you so much.

Answer 1

[Ilya]

Logistic regression on tall (out-of-memory) arrays is supported in 16b through the fitglm function.