In real analysis and approximation theory, the Kolmogorov–Arnold representation theorem (or superposition theorem) states that every multivariable continuous function can be represented as a superposition of continuous functions of two variables. It solved a version of Hilbert's thirteenth problem.
The works of Kolmogorov and Arnold established that if f is a multivariate continuous function, then f can be written as a finite composition of continuous functions of a single variable and the binary operation of addition.
More specifically
f
(
x
)
=
f
(
x
1
,
.
.
.
,
x
n
)
=
∑
q
=
0
2
n
Φ
q
(
∑
p
=
1
n
ϕ
q
,
p
(
x
p
)
)
.
Constructive proofs, and even more specific constructions can be found in
In a sense, they showed that the only true multivariate function is the sum, since every other function can be written using univariate functions and summing.
Kolmogorov–Arnold representation theorem is closely related to Hilbert's 13th problem. In his Paris lecture at the International Conference of Mathematicians in 1900, David Hilbert formulated 23 problems which in his opinion were important for the further development of mathematics. The 13th of these problems dealt with the solution of general equations of higher degrees. It is known that for algebraic equations of degree 4 the solution can be computed by formulae that only contain radicals and arithmetic operations. For higher orders, Galois' theory shows us that the solutions of algebraic equations cannot be expressed in terms of basic algebraic operations. It follows from the so called Tschirnhaus transformation that the general algebraic equation
x
n
+
a
n
−
1
x
n
−
1
+
⋅
⋅
⋅
+
a
0
=
0
can be translated to the form
y
n
+
b
n
−
4
y
n
−
4
+
⋅
⋅
⋅
+
b
1
y
+
1
=
0
. The Tschirnhaus transformation is given by a formula containing only radicals and arithmetic operations and transforms. Therefore, the solution of an algebraic equation of degree
n
can be represented as a superposition of functions of two variables if
n
<
7
and as a superposition of functions of
n
−
4
variables if
n
≥
7
. For
n
=
7
the solution is a superposition of arithmetic operations, radicals, and the solution of the equation
y
7
+
b
3
y
3
+
b
2
y
2
+
b
1
y
+
1
=
0
. A further simplification with algebraic transformations seems to be impossible which led to Hilbert's conjecture that "A solution of the general equation of degree 7 cannot be represented as a superposition of continuous functions of two variables". This explains the relation of Hilbert's thirteenth problem to the representation of a higher-dimensional function as superposition of lower-dimensional functions. In this context, it has stimulated many studies in the theory of functions and other related problems by different authors.
A variant of Kolmogorov's theorem that reduces the number of outer functions
Φ
q
is due to Lorentz. He showed in 1962 that the outer functions
Φ
q
can be replaced by a single function
Φ
. More precisely, Lorentz proved the existence of functions
ϕ
q
,
p
,
q
=
0
,
1
,
.
.
.
,
2
n
,
p
=
1
,
.
.
.
,
n
,
such that
f
(
x
)
=
∑
q
=
0
2
n
Φ
(
∑
p
=
1
n
ϕ
q
,
p
(
x
p
)
)
.
Sprecher replaced the inner functions
ϕ
q
,
p
by one single inner function with an appropriate shift in its argument. He proved that there exist real values
η
,
λ
1
,
.
.
.
,
λ
n
, a continuous function
Φ
:
R
→
R
and a real increasing continuous function
ϕ
:
[
0
,
1
]
→
[
0
,
1
]
with
ϕ
∈
L
i
p
(
l
n
2
/
l
n
(
2
N
+
2
)
)
,
N
≥
n
≥
2
, such that
f
(
x
)
=
∑
q
=
0
2
n
Φ
(
∑
p
=
1
n
λ
p
ϕ
(
x
p
+
η
q
)
+
q
)
.
Ostrand generalized the Kolmogorov superposition theorem to compact metric spaces. For
p
=
1
,
.
.
.
,
m
let
X
p
be compact metric spaces of finite dimension
n
p
and let
n
=
∑
p
=
1
m
n
p
. Then there exists continuous functions
ϕ
q
,
p
:
X
p
→
[
0
,
1
]
,
q
=
0
,
.
.
.
,
2
n
,
p
=
1
,
.
.
.
,
m
and continuous functions
G
q
:
[
0
,
1
]
→
R
,
q
=
0
,
.
.
.
,
2
n
such that any continuous function
f
:
X
1
×
⋅
×
X
m
→
R
is representable in the form
f
(
x
1
,
.
.
.
,
x
m
)
=
∑
q
=
0
2
n
G
q
(
∑
p
=
1
m
ϕ
q
,
p
(
x
p
)
)
.
