How to use the autogluon.optimizer.utils.Optimizer function in autogluon

def Ftrl(**kwargs):
    return Optimizer('ftrl')

The initial number of updates.

        multi_precision : bool, optional
           Flag to control the internal precision of the optimizer.::

               False: results in using the same precision as the weights (default),
               True: makes internal 32-bit copy of the weights and applies gradients
               in 32-bit precision even if actual weights used in the model have lower precision.
               Turning this on can improve convergence and accuracy when training with float16.
    """
    name = name.lower()
    if name not in optims:
        err_str = '"%s" is not among the following optimizer list:\n\t' % (name)
        err_str += '%s' % ('\n\t'.join(sorted(optims)))
        raise ValueError(err_str)
    optim = Optimizer(name)
    return optim

def FTML(**kwargs):
    return Optimizer('ftml')

def _get_search_space_strs(self):
        optim_strs = []
        for optim in self.optim_list:
            if isinstance(optim, Optimizer):
                optim_strs.append(optim.name)
            elif isinstance(optim, str):
                optim_strs.append(optim)
            else:
                raise NotImplementedError
        return optim_strs

def Adam(**kwargs):
    return Optimizer('adam')

def DCASGD(**kwargs):
    return Optimizer('dcasgd')

def LBSGD(**kwargs):
    return Optimizer('lbsgd')

def Signum(**kwargs):
    return Optimizer('signum')

def Nadam(**kwargs):
    return Optimizer('nadam')