What is the default learning rate, optimizer and activation function in Tensorflow's estimator API?

Question

Suppose we have LinearRegressor and DNNLinearRegressor models available in the Tensorflow estimator API.

However, the documentation does not clearly mention what the default optimizers, learning rate and activation functions are used by this API.

Please, let me know if you know the answer to this.

Thanks.

Answer 1

• If you look at LinearRegressor for you will see the default optimizer is FTRL with yet undefined learning rate. Mean squared error is used as a loss function.
• Moreover, DNNRegressor uses Adagrad optimizer with undefined learning rate and ReLU activations.

As you can see, everything is there. Hope that helps.