Patrick Reany
29 August 2025
Note: This chat I had with Copilot is likely edited for relevance and brevity. (Naturally, I get to correct my spelling and grammar errors for free.)
Patrick:
In the context of representation theory, what does the claim: "all finite groups are linear" mean? Does it mean that for each such group there can be found a homomorphism of that group into GL($V$)?
Copilot:
Yes, Patrick---your interpretation is spot on. The claim "all finite groups are linear" means precisely that every finite group $G$ admits a faithful representation as a group of invertible linear transformations on a finite-dimensional vector space. In formal terms:
There exists a group homomorphism \begin{equation} \rho : 𝐺\rightarrow \mbox{GL($V$)} \end{equation} for some finite-dimensional vector space $V$ over a field $F$, such that $\rho$ is injective.This means $G$ can be realized as a subgroup of the general linear group GL($V$), i.e., the group of invertible $n\times n$ matrices over $F$, for some $n=$ dim $V$.
Why Is This True?
This result is a consequence of Cayley's Theorem, which states that every group $G$ is isomorphic to a subgroup of the symmetric group $S_{|G|}$. Since permutation groups can be represented by permutation matrices (which are invertible), this gives a concrete embedding of $G$ into GL$_{|G|}(F)$ for any field $F$ of characteristic not dividing $|G|$.
Moreover, over fields of characteristic zero (or sufficiently large characteristic), Maschke's Theorem ensures that every representation of a finite group is completely reducible, allowing us to study $G$ via its irreducible components.
Faithful vs. Non-Faithful Representations
Example
Let $G=C_3=\{e,g,g^2\}$, the cyclic group of order 3. One linear representation is: \begin{equation} \rho(g)=\begin{pmatrix} \cos(2𝜋/3)& -\sin(2𝜋/3)\\ \sin(2𝜋/3)& \cos(2𝜋/3)) \end{pmatrix} \end{equation} This maps $G$ into GL$_2(R)$, faithfully representing its rotation symmetry.
Would you like to explore how this plays out in the context of character theory or how it generalizes to infinite groups and Lie groups?
Patrick:
What is Maschke's Theorem? Is that from module theory?
Copilot:
Absolutely, Patrick---Maschke's Theorem is a cornerstone of finite group representation theory, and yes, it has a powerful formulation in module-theoretic language. Let's unpack it from both perspectives:
Group-Theoretic Formulation
Maschke's Theorem states:
> If \( G \) is a finite group and \( F \) is a field whose characteristic does not divide the order of \( G \), then every finite-dimensional representation of \( G \) over \( F \) is completely reducible.
This means any representation \( \rho: G \to \mathrm{GL}(V) \) can be decomposed as a direct sum of irreducible subrepresentations: \[ V \cong V_1 \oplus V_2 \oplus \cdots \oplus V_k \] where each \( V_i \) is an irreducible \( G \)-invariant subspace.
Module-Theoretic Formulation
In module language, representations of \( G \) over \( F \) correspond to modules over the group algebra \( F[G] \). Maschke's Theorem then becomes:
> If \( \text{char}(F) \nmid |G| \), then the group algebra \( F[G] \) is semisimple.This means every \( F[G] \)-module (i.e., representation of \( G \)) is a direct sum of simple modules. In categorical terms, the category of \( F[G] \)-modules is semisimple: every object decomposes into a direct sum of irreducibles, and every short exact sequence splits.
Why the Characteristic Condition?
If the characteristic of \( F \) divides \( |G| \), then averaging arguments (used in the proof) break down. For example, the projection operator onto a subrepresentation involves dividing by \( |G| \), which fails in modular arithmetic when \( |G| = 0 \) in \( F \).
Example
Let \( G = C_2 = \{e, g\} \), and \( F = \mathbb{C} \). Any representation of \( G \) over \( \mathbb{C} \) can be decomposed into irreducibles---either the trivial representation or the sign representation. But if \( F = \mathbb{F}_2 \), the field with two elements, then \( \text{char}(F) = 2 \mid |G| \), and Maschke's Theorem does not apply.
Would you like to see how this connects to Wedderburn's Theorem or explore the structure of \( F[G] \) as a semisimple algebra? We could even sketch the categorical equivalence between representations and modules.