botorch.gen

Candidate generation utilities.

botorch.gen.gen_candidates_scipy(initial_conditions, acquisition_function, lower_bounds=None, upper_bounds=None, inequality_constraints=None, equality_constraints=None, options=None, fixed_features=None)[source]

Generate a set of candidates using scipy.optimize.minimize.

Optimizes an acquisition function starting from a set of initial candidates using scipy.optimize.minimize via a numpy converter.

Parameters

  • initial_conditions (Tensor) – Starting points for optimization.

  • acquisition_function (Module) – Acquisition function to be used.

  • lower_bounds (Union[float, Tensor, None]) – Minimum values for each column of initial_conditions.

  • upper_bounds (Union[float, Tensor, None]) – Maximum values for each column of initial_conditions.

  • constraints (equality) – A list of tuples (indices, coefficients, rhs), with each tuple encoding an inequality constraint of the form sum_i (X[indices[i]] * coefficients[i]) >= rhs.

  • constraints – A list of tuples (indices, coefficients, rhs), with each tuple encoding an inequality constraint of the form sum_i (X[indices[i]] * coefficients[i]) = rhs.

  • options (Optional[Dict[str, Any]]) – Options used to control the optimization including “method” and “maxiter”. Select method for scipy.minimize using the method” key. By default uses L-BFGS-B for box-constrained problems and SLSQP if inequality or equality constraints are present.

  • fixed_features (Optional[Dict[int, Optional[float]]]) – This is a dictionary of feature indices to values, where all generated candidates will have features fixed to these values. If the dictionary value is None, then that feature will just be fixed to the clamped value and not optimized. Assumes values to be compatible with lower_bounds and upper_bounds!

Return type

Tuple[Tensor, Tensor]

Returns

2-element tuple containing

  • The set of generated candidates.

  • The acquisition value for each t-batch.

Example

>>> qEI = qExpectedImprovement(model, best_f=0.2)
>>> bounds = torch.tensor([[0., 0.], [1., 2.]])
>>> Xinit = gen_batch_initial_conditions(
>>>     qEI, bounds, q=3, num_restarts=25, raw_samples=500
>>> )
>>> batch_candidates, batch_acq_values = gen_candidates_scipy(
        initial_conditions=Xinit,
        acquisition_function=qEI,
        lower_bounds=bounds[0],
        upper_bounds=bounds[1],
    )
botorch.gen.gen_candidates_torch(initial_conditions, acquisition_function, lower_bounds=None, upper_bounds=None, optimizer=<class 'torch.optim.adam.Adam'>, options=None, verbose=True, fixed_features=None)[source]

Generate a set of candidates using a torch.optim optimizer.

Optimizes an acquisition function starting from a set of initial candidates using an optimizer from torch.optim.

Parameters

  • initial_conditions (Tensor) – Starting points for optimization.

  • acquisition_function (Callable) – Acquisition function to be used.

  • lower_bounds (Union[float, Tensor, None]) – Minimum values for each column of initial_conditions.

  • upper_bounds (Union[float, Tensor, None]) – Maximum values for each column of initial_conditions.

  • optimizer (Optimizer) – The pytorch optimizer to use to perform candidate search.

  • options (Optional[Dict[str, Union[float, str]]]) – Options used to control the optimization. Includes maxiter: Maximum number of iterations

  • verbose (bool) – If True, provide verbose output.

  • fixed_features (Optional[Dict[int, Optional[float]]]) – This is a dictionary of feature indices to values, where all generated candidates will have features fixed to these values. If the dictionary value is None, then that feature will just be fixed to the clamped value and not optimized. Assumes values to be compatible with lower_bounds and upper_bounds!

Return type

Tuple[Tensor, Tensor]

Returns

2-element tuple containing

  • The set of generated candidates.

  • The acquisition value for each t-batch.

Example

>>> qEI = qExpectedImprovement(model, best_f=0.2)
>>> bounds = torch.tensor([[0., 0.], [1., 2.]])
>>> Xinit = gen_batch_initial_conditions(
>>>     qEI, bounds, q=3, num_restarts=25, raw_samples=500
>>> )
>>> batch_candidates, batch_acq_values = gen_candidates_torch(
        initial_conditions=Xinit,
        acquisition_function=qEI,
        lower_bounds=bounds[0],
        upper_bounds=bounds[1],
    )
botorch.gen.get_best_candidates(batch_candidates, batch_values)[source]

Extract best (q-batch) candidate from batch of candidates

Parameters

  • batch_candidates (Tensor) – A b x q x d tensor of b q-batch candidates, or a b x d tensor of b single-point candidates.

  • batch_values (Tensor) – A tensor with b elements containing the value of the respective candidate (higher is better).

Return type

Tensor

Returns

A tensor of size q x d (if q-batch mode) or d from batch_candidates with the highest associated value.

Example

>>> qEI = qExpectedImprovement(model, best_f=0.2)
>>> bounds = torch.tensor([[0., 0.], [1., 2.]])
>>> Xinit = gen_batch_initial_conditions(
>>>     qEI, bounds, q=3, num_restarts=25, raw_samples=500
>>> )
>>> batch_candidates, batch_acq_values = gen_candidates_scipy(
        initial_conditions=Xinit,
        acquisition_function=qEI,
        lower_bounds=bounds[0],
        upper_bounds=bounds[1],
    )
>>> best_candidates = get_best_candidates(batch_candidates, batch_acq_values)