def set_X_pending()

in botorch/acquisition/multi_objective/monte_carlo.py [0:0]

• 31 lines of code
• 7 McCabe index (conditional complexity)

    def set_X_pending(self, X_pending: Optional[Tensor] = None) -> None:
        r"""Informs the acquisition function about pending design points.

        Args:
            X_pending: `n x d` Tensor with `n` `d`-dim design points that have
                been submitted for evaluation but have not yet been evaluated.
        """
        if X_pending is None:
            self.X_pending = None
        else:
            if X_pending.requires_grad:
                warnings.warn(
                    "Pending points require a gradient but the acquisition function"
                    " will not provide a gradient to these points.",
                    BotorchWarning,
                )
            X_pending = X_pending.detach().clone()
            if self.cache_pending:
                X_baseline = torch.cat([self._X_baseline, X_pending], dim=-2)
                # Number of new points is the total number of points minus
                # (the number of previously cached pending points plus the
                # of number of baseline points).
                num_new_points = X_baseline.shape[0] - self.X_baseline.shape[0]
                if num_new_points > 0:
                    if num_new_points > self._max_iep:
                        # Set the new baseline points to include pending points.
                        self.register_buffer("_X_baseline_and_pending", X_baseline)
                        # Recompute box decompositions.
                        self._set_cell_bounds(num_new_points=num_new_points)
                        if not self.incremental_nehvi:
                            self._prev_nehvi = (
                                (self._hypervolumes - self._initial_hvs)
                                .clamp_min(0.0)
                                .mean()
                            )
                        # Set to None so that pending points are not concatenated in
                        # forward.
                        self.X_pending = None
                        # Set q_in=-1 to so that self.sampler is updated at the next
                        # forward call.
                        self.q_in = -1
                    else:
                        self.X_pending = X_pending[-num_new_points:]
            else:
                self.X_pending = X_pending