Categorical semantics

Constructing denotational models of linear can be a tedious work. Categorical model are useful to identify the fundamental structure of these models, and thus simplify and make more abstract the elaboration of those models.

TODO: why categories? how to extract categorical models? etc.

See for a more detailed introduction to category theory.

Modeling IMLL

A model of IMLL is a closed symmetric monoidal category. We recall the definition of these categories below.

Definition (Monoidal category)

A monoidal category $(\mathcal{C},\otimes,I,\alpha,\lambda,\rho)$ is a category $\mathcal{C}$ equipped with

• a functor $\otimes:\mathcal{C}\times\mathcal{C}\to\mathcal{C}$ called tensor product,
• an object I called unit object,
• three natural isomorphisms α, λ and ρ, called respectively associator, left unitor and right unitor, whose components are

$\alpha_{A,B,C}:(A\otimes B)\otimes C\to A\otimes (B\otimes C) \qquad \lambda_A:I\otimes A\to A \qquad \rho_A:A\otimes I\to A$

such that

• for every objects A,B,C,D in $\mathcal{C}$, the diagram

commutes,

• for every objects A and B in $\mathcal{C}$, the diagrams

commute.

Definition (Braided, symmetric monoidal category)

A braided monoidal category is a category together with a natural isomorphism of components

$\gamma_{A,B}:A\otimes B\to B\otimes A$

called braiding, such that the two diagrams

UNIQ6e5447295cf39b8e-math-00000011-QINU

commute for every objects A, B and C.

A symmetric monoidal category is a braided monoidal category in which the braiding satisfies

$\gamma_{B,A}\circ\gamma_{A,B}=A\otimes B$

for every objects A and B.

Definition (Closed monoidal category)

A monoidal category $(\mathcal{C},\tens,I)$ is left closed when for every object A, the functor

$B\mapsto A\otimes B$

has a right adjoint, written

$B\mapsto(A\limp B)$

This means that there exists a bijection

$\mathcal{C}(A\tens B, C) \cong \mathcal{C}(B,A\limp C)$

which is natural in B and C. Equivalently, a monoidal category is left closed when it is equipped with a left closed structure, which consists of

• an object $A\limp B$,
• a morphism $\mathrm{eval}_{A,B}:A\tens (A\limp B)\to B$, called left evaluation,

for every objects A and B, such that for every morphism $f:A\otimes X\to B$ there exists a unique morphism $h:X\to A\limp B$ making the diagram

TODO

commute.

Dually, the monoidal category $\mathcal{C}$ is right closed when the functor $B\mapsto B\otimes A$ admits a right adjoint. The notion of right closed structure can be defined similarly.

In a symmetric monoidal category, a left closed structure induces a right closed structure and conversely, allowing us to simply speak of a closed symmetric monoidal category.

Modeling the additives

Definition (Product)

Definition (Monoid)

Property

Categories with products vs monoidal categories.

Modeling IMALL

Definition (Linear-non linear (LNL) adjunction)

A linear-non linear adjunction is a symmetric monoidal adjunction between lax monoidal functors

$(\mathcal{M},\times,\top) TODO (\mathcal{L},\otimes,I)$

in which the category $\mathcal{M}$ has finite products.

Modeling negation

Definition (*-autonomous category)

Suppose that we are given a symmetric monoidal closed category $(\mathcal{C},\tens,I)$ and an object R of $\mathcal{C}$. For every object A, we define a morphism

$\partial_{A}:A\to(A\limp R)\limp R$

as follows. By applying the bijection of the adjunction defining (left) closed monoidal categories to the identity morphism $\mathrm{id}_{A\limp R}:A\limp R \to A\limp R$, we get a morphism $A\tens (A\limp R)\to R$, and thus a morphism $(A\limp R)\tens A\to R$ by precomposing with the symmetry $\gamma_{A\limp R,A}$. The morphism $\partial_A$ is finally obtained by applying the bijection of the adjunction defining (left) closed monoidal categories to this morphism. The object R is called dualizing when the morphism $\partial_A$ is a bijection for every object A of $\mathcal{C}$. A symmetric monoidal closed category is *-autonomous when it admits such a dualizing object.