torch.optim.functional.adamax

torch.optim.functional.adamax(params, grads, exp_avgs, exp_infs, state_steps, foreach=None, maximize=False, differentiable=False, capturable=False, has_complex=False, *, eps, beta1, beta2, lr, weight_decay)

Functional API that performs Adamax algorithm computation.

This function updates the provided parameters and optimizer state in place. The caller must initialize and retain optimizer state. Unless intentionally constructing a differentiable update with a supported differentiable=True argument, call this function under torch.no_grad. See Functional optimizer API for the common functional optimizer contract and examples, and Adamax for algorithm details.