TABULARGAN Procedure

GANOPTIMIZATION Statement

GANOPTIMIZATION < ADAM(suboptions) > < options >;

The GANOPTIMIZATION statement specifies the optimizer parameters to use in training the GAN model. You can specify the following options:

ADAM (BETA1=number BETA2=number)

specifies the optimization method to use in training the GAN model. Currently only the Adam method is supported. You must specify the keyword ADAM when specifying the following suboptions:

BETA1=number

specifies the exponential decay rate for the first-moment estimates.

By default, BETA1=0.5.

BETA2=number

specifies the exponential decay rate for the second-moment estimates.

By default, BETA2=0.9.

LEARNINGRATE=number

specifies the learning rate for the optimizer.

By default, LEARNINGRATE=0.00002.

NUMEPOCHS=number

specifies the number of epochs to use in training the model GAN model. The number must be a positive integer.

By default, NUMEPOCHS=150.

WEIGHTDECAYD=number

specifies the weight decay for the discriminator’s optimizer.

By default, WEIGHTDECAYD=0.0001.

WEIGHTDECAYG=number

specifies the weight decay for the generator’s optimizer.

By default, WEIGHTDECAYG=0.000001.

Last updated: September 23, 2026