Covering number

Not to be confused with Winding number or degree of a continuous mapping, sometimes called "covering number" or "engulfing number".

In mathematics, a covering number is the number of spherical balls of a given size needed to completely cover a given space, with possible overlaps. Two related concepts are the packing number, the number of disjoint balls that fit in a space, and the metric entropy, the number of points that fit in a space when constrained to lie at some fixed minimum distance apart.

Definition

Let (M, d) be a metric space, let K be a subset of M, and let r be a positive real number. Let B_r(x) denote the ball of radius r centered at x. A subset C of M is an r-external covering of K if:

$K\subseteq \cup _{x\in C}B_{r}(x)$.

In other words, for every $y\in K$ there exists $x\in C$ such that $d(x,y)\leq r$.

If furthermore C is a subset of K, then it is an r-internal covering.

The external covering number of K, denoted $N_{r}^{\text{ext}}(K)$, is the minimum cardinality of any external covering of K. The internal covering number, denoted $N_{r}^{\text{int}}(K)$, is the minimum cardinality of any internal covering.

A subset P of K is a packing if $P\subseteq K$ and the set $\{B_{r}(x)\}_{x\in P}$ is pairwise disjoint. The packing number of K, denoted $N_{r}^{\text{pack}}(K)$, is the maximum cardinality of any packing of K.

A subset S of K is r-separated if each pair of points x and y in S satisfies d(x, y) ≥ r. The metric entropy of K, denoted $N_{r}^{\text{met}}(K)$, is the maximum cardinality of any r-separated subset of K.

Examples

1. The metric space is the real line $\mathbb {R}$. $K\subset \mathbb {R}$ is a set of real numbers whose absolute value is at most $k$. Then, there is an external covering of $\lceil 2k/r\rceil$ intervals of length $r$, covering the interval $[k,-k]$. Hence:

$N_{r}^{\text{ext}}(K)\leq (2k/r)$

2. The metric space is the Euclidean space $\mathbb {R} ^{m}$ with the Euclidean metric. $K\subset \mathbb {R} ^{m}$ is a set of vectors whose length (norm) is at most $k$. If $K$ lies in a d-dimensional subspace of $\mathbb {R} ^{m}$, then:

$N_{r}^{\text{ext}}(K)\leq (2k{\sqrt {d}}/r)^{d}$.

3. The metric space is the space of real-valued functions, with the l-infinity metric. The covering number $N_{r}^{\text{int}}(K)$ is the smallest number $k$ such that, there exist $h_{1},\ldots ,h_{k}\in K$ such that, for all $h\in K$ there exists $i\in \{1,\ldots ,k\}$ such that the supremum distance between $h$ and $h_{i}$ is at most $r$. The above bound is not relevant since the space is $\infty$-dimensional. However, when $K$ is a compact set, every covering of it has a finite sub-covering, so $N_{r}^{\text{int}}(K)$ is finite.

Properties

1. The internal and external covering numbers, the packing number, and the metric entropy are all closely related. The following chain of inequalities holds for any subset K of a metric space and any positive real number r.

$N_{2r}^{\text{met}}(K)\leq N_{r}^{\text{pack}}(K)\leq N_{r}^{\text{ext}}(K)\leq N_{r}^{\text{int}}(K)\leq N_{r}^{\text{met}}(K)$

2. Each function except the internal covering number is non-increasing in r and non-decreasing in K. The internal covering number is monotone in r but not necessarily in K.

The following properties relate to covering numbers in the standard Euclidean space $\mathbb {R} ^{m}$:

3. If all vectors in $K$ are translated by a constant vector $k_{0}\in \mathbb {R} ^{m}$, then the covering number does not change.

4. If all vectors in $K$ are multiplied by a scalar $k\in \mathbb {R}$, then:

for all $r$: $N_{|k|\cdot r}^{\text{ext}}(k\cdot K)=N_{r}^{\text{ext}}(K)$

5. If all vectors in $K$ are operated by a Lipschitz function $\phi$ with Lipschitz constant $k$, then:

for all $r$: $N_{|k|\cdot r}^{\text{ext}}(\phi \circ K)\leq N_{r}^{\text{ext}}(K)$

Application to machine learning

Let $K$ be a space of real-valued functions, with the l-infinity metric (see example 3 above). Suppose all functions in $K$ are bounded by a real constant $M$. Then, the covering number can be used to bound the generalization error of learning functions from $K$, relative to the squared loss:

$\mathrm {Prob} {\big [}\sup _{h\in K}|{\text{GeneralizationError}}(h)-{\text{EmpiricalError}}(h)|\geq \epsilon {\big ]}\leq N_{r}^{\text{int}}(K)\cdot 2\exp {-m\epsilon ^{2} \over 2M^{4}}$

where $r={\epsilon \over 8M}$ and $m$ is the number of samples.

See also

• Polygon covering
• Kissing number