More efficient 'tell_many'

import adaptive

def f(x, offset=0):
    a = 0.01
    return x + a**2 / (a**2 + (x - offset)**2)

learner = adaptive.Learner1D(f, bounds=(-1, 1))
adaptive.runner.simple(learner, goal=lambda l: l.npoints > 200)

Timing new implementation

%%timeit
learner2 = adaptive.Learner1D(f, bounds=(-1, 1))
learner2.tell_many(*zip(*learner.data.items()))

1.17 ms ± 24.9 µs per loop (mean ± std. dev. of 7 runs, 1000 loops each)

Timing old implementation

%%timeit
learner2 = adaptive.Learner1D(f, bounds=(-1, 1))
for x, y in learner.data.items():
    learner2.tell(x, y)

6.82 ms ± 447 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)

This makes it ~6 times faster for functions that return scalars and is >10 times faster for vectors.

adaptive/learner/average_learner.py

@@ -14,12 +14,19 @@ class AverageLearner(BaseLearner):
     The learned function must depend on an integer input variable that
     represents the source of randomness.
 
-    Parameters:
-    -----------
+    Parameters
+    ----------
     atol : float
         Desired absolute tolerance
     rtol : float
         Desired relative tolerance
+
+    Attributes
+    ----------
+    data : dict
+        Sampled points and values.
+    pending_points : set
+        Points that still have to be evaluated.
     """
 
     def __init__(self, function, atol=None, rtol=None):
@@ -31,6 +38,7 @@ class AverageLearner(BaseLearner):
             rtol = np.inf
 
         self.data = {}
+        self.pending_points = set()
         self.function = function
         self.atol = atol
         self.rtol = rtol
@@ -40,28 +48,36 @@ class AverageLearner(BaseLearner):
 
     @property
     def n_requested(self):
-        return len(self.data)
+        return len(self.data) + len(self.pending_points)
 
-    def ask(self, n, add_data=True):
+    def ask(self, n, tell_pending=True):
         points = list(range(self.n_requested, self.n_requested + n))
+
+        if any(p in self.data or p in self.pending_points for p in points):
+            # This means some of the points `< self.n_requested` do not exist.
+            points = list(set(range(self.n_requested + n))
+                          - set(self.data)
+                          - set(self.pending_points))[:n]
+
         loss_improvements = [self.loss_improvement(n) / n] * n
-        if add_data:
-            self.tell_many(points, itertools.repeat(None))
+        if tell_pending:
+            for p in points:
+                self.tell_pending(p)
         return points, loss_improvements
 
     def tell(self, n, value):
-        value_is_new = not (n in self.data and value == self.data[n])
-        if not value_is_new:
-            value_old = self.data[n]
+        if n in self.data:
+            # The point has already been added before.
+            return
+
         self.data[n] = value
-        if value is not None:
-            self.sum_f += value
-            self.sum_f_sq += value**2
-            if value_is_new:
-                self.npoints += 1
-            else:
-                self.sum_f -= value_old
-                self.sum_f_sq -= value_old**2
+        self.pending_points.discard(n)
+        self.sum_f += value
+        self.sum_f_sq += value**2
+        self.npoints += 1
+
+    def tell_pending(self, n):
+        self.pending_points.add(n)
 
     @property
     def mean(self):
@@ -94,7 +110,7 @@ class AverageLearner(BaseLearner):
 
     def remove_unfinished(self):
         """Remove uncomputed data from the learner."""
-        pass
+        self.pending_points = set()
 
     def plot(self):
         hv = ensure_holoviews()