torch.optim.functional.adadelta

torch.optim.functional.adadelta(params, grads, square_avgs, acc_deltas, state_steps, capturable=False, foreach=None, differentiable=False, has_complex=False, *, lr, rho, eps, weight_decay, maximize)

Functional API that performs Adadelta 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 Adadelta for algorithm details.