syne_tune/optimizer/schedulers/searchers/gp_searcher_factory.py [422:436]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    exponent_cost = kwargs.get('exponent_cost', 1.0)
    acquisition_class = (
        EIpuAcquisitionFunction, dict(exponent_cost=exponent_cost))
    # The same skip_optimization strategy applies to both models
    skip_optimization_cost = skip_optimization

    output_model_factory = {INTERNAL_METRIC_NAME: model_factory,
                            INTERNAL_COST_NAME: model_factory_cost}
    output_skip_optimization = {INTERNAL_METRIC_NAME: skip_optimization,
                                INTERNAL_COST_NAME: skip_optimization_cost}

    return dict(result,
                **_kwargs_int_common(kwargs),
                output_model_factory=output_model_factory,
                output_skip_optimization=output_skip_optimization,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



syne_tune/optimizer/schedulers/searchers/gp_searcher_factory.py [476:490]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    exponent_cost = kwargs.get('exponent_cost', 1.0)
    acquisition_class = (
        EIpuAcquisitionFunction, dict(exponent_cost=exponent_cost))
    # The same skip_optimization strategy applies to both models
    skip_optimization_cost = skip_optimization

    output_model_factory = {INTERNAL_METRIC_NAME: model_factory,
                            INTERNAL_COST_NAME: model_factory_cost}
    output_skip_optimization = {INTERNAL_METRIC_NAME: skip_optimization,
                                INTERNAL_COST_NAME: skip_optimization_cost}

    return dict(result,
                **_kwargs_int_common(kwargs),
                output_model_factory=output_model_factory,
                output_skip_optimization=output_skip_optimization,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -