def evaluate()

in botorch/optim/stopping.py [0:0]

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

    def evaluate(self, fvals: Tensor) -> bool:
        r"""Evaluate the stopping criterion.

        Args:
            fvals: tensor containing function values for the current iteration. If
                `fvals` contains more than one element, then the stopping criterion is
                evaluated element-wise and True is returned if the stopping criterion is
                true for all elements.

        TODO: add support for utilizing gradient information

        Returns:
            Stopping indicator (if True, stop the optimziation).
        """
        self.iter += 1
        if self.iter == self.maxiter:
            return True

        if self._prev_fvals is None:
            self._prev_fvals = fvals.unsqueeze(0)
        else:
            self._prev_fvals = torch.cat(
                [self._prev_fvals[-self.n_window :], fvals.unsqueeze(0)]
            )

        if self._prev_fvals.size(0) < self.n_window + 1:
            return False

        weights = self.weights
        weights = weights.to(fvals)
        if self._prev_fvals.ndim > 1:
            weights = weights.unsqueeze(-1)

        # TODO: Update the exp moving average efficiently
        prev_ma = (self._prev_fvals[:-1] * weights).sum(dim=0)
        ma = (self._prev_fvals[1:] * weights).sum(dim=0)
        # TODO: Handle approx. zero losses (normalize by min/max loss range)
        rel_delta = (prev_ma - ma) / prev_ma.abs()

        if not self.minimize:
            rel_delta = -rel_delta
        if torch.max(rel_delta) < self.rel_tol:
            return True

        return False