Merge pull request #684 from gchq/feature/improve-coreset-docs

docs: simplify `Coreax.Coreset` docstring maths

Author: pc532627

.cspell/library_terms.txt

@@ -83,6 +83,7 @@ ndim
 newaxis
 nobs
 nonzero
+notin
 numpy
 opencv
 operatorname

coreax/coreset.py

@@ -35,41 +35,16 @@ class Coreset(eqx.Module, Generic[_Data]):
     r"""
     Data structure for representing a coreset.
 
-    TLDR: a coreset is a reduced set of :math:`\hat{n}` (potentially weighted) data
-    points that, in some sense, best represent the "important" properties of a larger
-    set of :math:`n > \hat{n}` (potentially weighted) data points.
+    A coreset is a reduced set of :math:`\hat{n}` (potentially weighted) data points,
+    :math:`\hat{X} := \{(\hat{x}_i, \hat{w}_i)\}_{i=1}^\hat{n}` that, in some sense,
+    best represent the "important" properties of a larger set of :math:`n > \hat{n}`
+    (potentially weighted) data points :math:`X := \{(x_i, w_i)\}_{i=1}^n`.
 
-    Given a dataset :math:`X = \{x_i\}_{i=1}^n, x \in \Omega`, where each node is paired
-    with a non-negative (probability) weight :math:`w_i \in \mathbb{R} \ge 0`, there
-    exists an implied discrete (probability) measure over :math:`\Omega`
+    :math:`\hat{x}_i, x_i \in \Omega` represent the data points/nodes and
+    :math:`\hat{w}_i, w_i \in \mathbb{R}` represent the associated weights.
 
-    .. math::
-        \eta_n = \sum_{i=1}^{n} w_i \delta_{x_i}.
-
-    If we then specify a set of test-functions :math:`\Phi = {\phi_1, \dots, \phi_M}`,
-    where :math:`\phi_i \colon \Omega \to \mathbb{R}`, which somehow capture the
-    "important" properties of the data, then there also exists an implied push-forward
-    measure over :math:`\mathbb{R}^M`
-
-    .. math::
-        \mu_n = \sum_{i=1}^{n} w_i \delta_{\Phi(x_i)}.
-
-    A coreset is simply a reduced measure containing :math:`\hat{n} < n` updated nodes
-    :math:`\hat{x}_i` and weights :math:`\hat{w}_i`, such that the push-forward measure
-    of the coreset :math:`\nu_\hat{n}` has (approximately for some algorithms) the same
-    "centre-of-mass" as the push-forward measure for the original data :math:`\mu_n`
-
-    .. math::
-        \text{CoM}(\mu_n) = \text{CoM}(\nu_\hat{n}),
-        \text{CoM}(\nu_\hat{n}) = \int_\Omega \Phi(\omega) d\nu_\hat{x}(\omega),
-        \text{CoM}(\nu_\hat{n}) = \sum_{i=1}^\hat{n} \hat{w}_i \delta_{\Phi(\hat{x}_i)}.
-
-    .. note::
-        Depending on the algorithm, the test-functions may be explicitly specified by
-        the user, or implicitly defined by the algorithm's specific objectives.
-
-    :param nodes: The (weighted) coreset nodes, math:`x_i \in \text{supp}(\nu_\hat{n})`;
-        once instantiated, the nodes should be accessed via :meth:`Coresubset.coreset`
+    :param nodes: The (weighted) coreset nodes, :math:`\hat{x}_i`; once instantiated,
+        the nodes should only be accessed via :meth:`Coresubset.coreset`
     :param pre_coreset_data: The dataset :math:`X` used to construct the coreset.
     """
 
@@ -125,27 +100,24 @@ class Coresubset(Coreset[Data], Generic[_Data]):
     r"""
     Data structure for representing a coresubset.
 
-    A coresubset is a :class`Coreset`, with the additional condition that the support of
-    the reduced measure (the coreset), must be a subset of the support of the original
-    measure (the original data), such that
+    A coresubset is a :class:`Coreset`, with the additional condition that the coreset
+    data points/nodes must be a subset of the original data points/nodes, such that
 
     .. math::
         \hat{x}_i = x_i, \forall i \in I,
-        I \subset \{1, \dots, n\}, text{card}(I) = \hat{n}.
+        I \subset \{1, \dots, n\}, \text{card}(I) = \hat{n}.
 
     Thus, a coresubset, unlike a coreset, ensures that feasibility constraints on the
-    support of the measure are maintained :cite:`litterer2012recombination`. This is
-    vital if, for example, the test-functions are only defined on the support of the
-    original measure/nodes, rather than all of :math:`\Omega`.
+    support of the measure are maintained :cite:`litterer2012recombination`.
 
-    In coresubsets, the measure reduction can be implicit (setting weights/nodes to
-    zero for all :math:`i \in I \ {1, \dots, n}`) or explicit (removing entries from the
-    weight/node arrays). The implicit approach is useful when input/output array shape
-    stability is required (E.G. for some JAX transformations); the explicit approach is
-    more similar to a standard coreset.
+    In coresubsets, the dataset reduction can be implicit (setting weights/nodes to zero
+    for all :math:`i \notin I`) or explicit (removing entries from the weight/node
+    arrays). The implicit approach is useful when input/output array shape stability is
+    required (E.G. for some JAX transformations); the explicit approach is more similar
+    to a standard coreset.
 
     :param nodes: The (weighted) coresubset node indices, :math:`I`; the materialised
-        coresubset nodes should be accessed via :meth:`Coresubset.coreset`.
+        coresubset nodes should only be accessed via :meth:`Coresubset.coreset`.
     :param pre_coreset_data: The dataset :math:`X` used to construct the coreset.
     """