\(
\def\cuberoot#1{\sqrt[3]{#1}}
\def\fourthroot#1{\sqrt[4]{#1}}
\def\abspartial#1#2#3#4{\left|\,{\partial(#1,#2)\over\partial(#3,#4)}\,\right|}
\def\absdeltal#1#2#3#4{\left|\,{\d(#1,#2)\over\d(#3,#4)}\,\right|}
\def\dispop#1#2{\disfrac{\partial #1}{\partial #2}}
\def\definedas{\equiv}
\def\bb{{\bf b}}
\def\bB{{\bf B}}
\def\bsigma{\boldsymbol{\sigma}}
\def\bx{{\bf x}}
\def\bu{{\bf u}}
\def\Re{{\rm Re\hskip1pt}}
\def\Reals{{\mathbb R\hskip1pt}}
\def\Integers{{\mathbb Z\hskip1pt}}
\def\Im{{\rm Im\hskip1pt}}
\def\P{\mbox{P}}
\def\half{{\textstyle{1\over 2}}}
\def\third{{\textstyle{1\over3}}}
\def\fourth{{\textstyle{1\over 4}}}
\def\fifth{{\scriptstyle{1\over 5}}}
\def\sixth{{\textstyle{1\over 6}}}
\def\oA{\rlap{$A$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt}
\def\obA{\rlap{$A$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt}
\def\obX{\rlap{$X$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt}
\def\obY{\rlap{$Y$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt}
\def\obZ{\rlap{$Z$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt}
\def\obc{\rlap{$c$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt}
\def\obd{\rlap{$d$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt}
\def\obk{\rlap{$k$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt}
\def\oba{\rlap{$a$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt}
\def\obb{\rlap{$b$}\kern1pt\overline{\phantom{\dis{}t}}\kern.5pt}
\def\obw{\rlap{$w$}\kern1pt\overline{\phantom{\dis{}t}}\kern.5pt}
\def\obz{\overline{z}}\kern.5pt}
\newcommand{\bx}{\boldsymbol{x}}
\newcommand{\by}{\boldsymbol{y}}
\newcommand{\br}{\boldsymbol{r}}
\renewcommand{\bk}{\boldsymbol{k}}
\def\cuberoot#1{\sqrt[3]{#1}}
\def\fourthroot#1{\sqrt[4]{#1}}
\def\fifthroot#1{\sqrt[5]{#1}}
\def\eighthroot#1{\sqrt[8]{#1}}
\def\twelfthroot#1{\sqrt[12]{#1}}
\def\dis{\displaystyle}
%\def\definedas{\equiv}
\def\bq{{\bf q}}
\def\bp{{\bf p}}
\def\abs#1{\left|\,#1\,\right|}
\def\disfrac#1#2{{\displaystyle #1\over\displaystyle #2}}
\renewcommand{\ba}{\boldsymbol{a}}
\renewcommand{\bb}{\boldsymbol{b}}
\newcommand{\bc}{\boldsymbol{c}}
\newcommand{\bh}{\boldsymbol{h}}
\newcommand{\bA}{\boldsymbol{A}}
\newcommand{\bB}{\boldsymbol{B}}
\newcommand{\bC}{\boldsymbol{C}}
\newcommand{\definedas}{\equiv}
\newcommand{\half}{\frac{1}{2}}
\newcommand{\bsigma}{\boldsymbol \sigma}
\newcommand{\abs}[1]{\left|\,#1\,\right|}
\newcommand{\Rectangle}{\sqsubset\!\sqsupset}
\newcommand{\rectangle}{{%
\ooalign{$\sqsubset\mkern3mu$\cr$\mkern3mu\sqsupset$\cr}%
}}
\usepackage{amssymb}
\usepackage{amsmath}
\usepackage{amsfonts}
\)
Conformal Field Theories
Patrick Reany
19 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:
Is the conformal group a special type of Lie group?
Copilot:
Conformal Group as a Lie Group
Yes. The conformal group is itself a Lie group---indeed, a finite-dimensional, non-compact, semisimple Lie group when acting on flat space of dimension $\ge 3$. It consists of all smooth transformations that preserve angles (up to a local scaling), and it inherits both a smooth-manifold structure and a group structure compatible with smooth multiplication and inversion.
Key Features
- Manifold and Group
The conformal group is a differentiable manifold whose points are transformations. Composition and inversion of conformal maps are smooth, so it meets the definition of a Lie group.
- Generators and Algebra In $d$ dimensions $(d \ge 3)$, it is generated by
- Translations
- Rotations (or Lorentz boosts in signature $(p,q)$)
- Dilations (global rescalings)
- Special conformal transformations These satisfy the commutation relations of the Lie algebra
π π$(π+1,π+1)$.
Matrix Realization Up to a discrete identification, the group is isomorphic to
π$(π+1,π+1)β/β\{\pm1\}$, where $(π,π)$ is the signature of the underlying space (e.g., $(d,0)$ for Euclidean, $(d-1,1)$ for Minkowski).
Special and Exceptional Cases
- Two Dimensions
Locally, conformal transformations in two real dimensions form an infinite-dimensional group (the analytic diffeomorphisms of the Riemann sphere), whose algebra extends the finite π π(3,1) to the Virasoro algebra upon central extension.
Globally, the Mobius group PSL(2,$\mathbb C$) remains a finite cover of the conformal group on the Riemann sphere.
- Relation to Classical "Special" Groups Although called the "conformal group," it is not the same as Special Orthogonal (SO) or Special Linear (SL) groups in name, but it is semisimple like those "classical" groups.
Further Connections
- Conformal Field Theory In physics, this Lie group underpins conformal symmetry in critical phenomena and quantum field theories, with its representations classifying fields by scaling dimension and spin.
- Geometric Interpretation One can view the conformal group as the isometry group of the "conformal compactification" of flat space, realized as a projective lightcone in one higher dimension.
- Beyond Flat Space On a general Riemannian manifold, the full conformal "group" can be infinite dimensional (all local scalings preserving the metric up to a factor). However, additional curvature constraints typically reduce it back to a finite-dimensional Lie group.
By understanding the conformal group as a Lie group, you gain access to powerful tools---such as Lie algebra techniques, representation theory, and differential geometry---to analyze angle-preserving symmetries in mathematics and physics.
Patrick:
Physicist Tobias Osborne claims that the really interesting conformal groups are over two-dimensional manifolds, but isn't that just a slight generalization of conformal transformations over the complex plane?
Copilot:
Direct Answer
It's far more than a slight extension of the flat-plane case. In two real dimensions you unlock an infinite-dimensional symmetry: locally any holomorphic map is conformal, and globally the story depends on the topology (genus) of your Riemann surface. That richness underpins the heart of 2D conformal field theory.
From the Complex Plane to Riemann Surfaces
- On the complex plane (or the Riemann sphere), global conformal maps reduce to Mobius transformations (PSL(2,$\mathbb C$)), a finite-dimensional group.
- In two dimensions, if you allow arbitrary local holomorphic coordinate changes, the symmetry algebra becomes the Witt algebra, which upon quantization extends to the Virasoro algebra---infinitely many generators labeled by integer "modes."
- When you move off the plane to a compact Riemann surface of genus $g \ge1$, the global conformal (biholomorphic) group shrinks again---often to a finite group of automorphisms---but you still have the infinite local symmetry encoded in vertex operator algebras and the sewing of local patches.
Why Osborne Emphasizes 2D
- Infinite-Dimensional Local Symmetries Every holomorphic map fixing a point gives a new generator. That dramatic jump from four Mobius generators (translations, rotations, dilations, special conformal) to countably infinite ones is what makes 2D theories tractable yet profoundly rich.
- Moduli and Teichmuller Theory The conformal class of metrics on a genus-g surface is parameterized by a 6gβ6 real-dimensional Teichmuller space. Integrating over that space in string theory or summing over these moduli in statistical models is where geometry dances with physics.
- Central Charge & Anomalies
Only in two dimensions can the central extension (the "c-number" in the Virasoro algebra) dramatically affect classification of theories. That extra ingredient leads to minimal models, Liouville theory, and an entire zoo of solvable CFTs.
Beyond the Plane: What's Really New
- Local vs. Global: 2D CFT exploits local conformal invariance to build operator product expansions and bootstrap equations---tools unavailable if you're stuck with only global Mobius symmetry.
- Topological Variety: Each Riemann surface genus brings new partition functions, new modular forms, and new mapping-class-group actions that classify sectors of the theory.
- Holography & Strings: String world-sheets are 2D conformal manifolds, and their infinite symmetry constrains target-space physics (AdS3CFT2 being a prime example).
Where to Go from Here
If you're intrigued by how local holomorphic maps outsize the plane's Mobius group, you might explore:
- The structure of the Virasoro and affine Lie algebra representations in 2D CFT.
- Teichmuller theory and the mapping class group's role in moduli integrals.
- Applications to string perturbation theory, where 2D conformal symmetry governs consistency conditions.
Patrick:
Is there a connection to modular forms?
Copilot:
Connection Between 2D CFT and Modular Forms
The torus partition functions and chiral characters of a two-dimensional conformal field theory furnish examples of modular forms or modularβinvariant functions under the action of SL(2,$\mathbb{Z}$) on the complex structure $\tau$ of the torus.
Torus Partition Functions as Modular Invariants
- In a 2D CFT, placing the theory on a torus with complex modulus $\tau$
produces a partition function $Z(\tau, \overline{\tau}) =$ Tr$\_H (q^{L_0βc/24} \bar q^{\bar L_0βc/24})$, where $q = e^{2Οi\tau}$.
-
Modular transformations
$\tau \rightarrow (a\tau+ b)/(c\tau + d)$ with $\begin{pmatrix}π&π\\ π&π\end{pmatrix} \in \mbox{ππΏ(2,$\mathbb{Z}$)}$
leave $Z$ invariant:
$Z(π\tau+π)/(π\tau+π),(π\bar\tau+π)/(π\bar\tau+π) = Z(\tau, \bar\tau)$.
Chiral Characters and VectorβValued Modular Forms
- Each highestβweight representation of the Virasoro (or extended) algebra contributes a character $\chi h(\tau) = Tr{\cal H}_h(q^{L_0-c/24})$.
- The vector of characters $\{\chi_h\}$ forms a vectorβvalued modular form: under $\tau \rightarrow-1/\tau$ it mixes by an "S-matrix," and under $\tau \rightarrow\tau+1$ by a "T-matrix" (the Verlinde matrices).
CFT Object $\hskip1.75in$ Modular Behavior
Torus partition function $Z(\tau, \overline{\tau})$ $\hskip.25in$ Invariant under SL(2,$\mathbb Z$)
Chiral character $\chi_h(\tau)$ Transforms as a vectorβvalued modular form
Why Modular Forms Matter in 2D CFT
- Partition Function Constraints Modular invariance severely restricts the spectrum (allowed scaling dimensions and central charge) of a rational CFT.
- Modular Bootstrap By expanding $Z$ and $\chi\_h$ in $q$-series and demanding consistent modular transformations, one can solve or greatly constrain correlation functions and operator algebras.
- Moonshine and Beyond Monstrous and Umbral moonshine relate CFT characters to specific modular or mock modular forms, revealing deep ties between finite groups, vertex operator algebras, and number theory.
Further Reading and Directions
- arXiv:2208.07242 "Lectures on modular forms and strings" for an overview of modular invariance in CFT and string theory.
- Di Francesco, Mathieu, and Senechal, Conformal Field Theory (Chapter 6).
- Explore mock modular forms and their role in non-compact or logarithmic CFTs.
- Delve into the Eichler-Zagier theory of Jacobi forms when considering elliptic genera in supersymmetric theories.
Looking ahead, you might also explore how higherβgenus partition functions transform under mapping class groups, or how quantum modular forms emerge in three-dimensional topological field theories---each avenue weaving modular geometry deeper into modern mathematical physics.
Patrick:
Can you specify three features (theorems) of the conformal transformations on the complex plane that are most useful in the study/development of CFT?
Copilot:
Three Pillars of Planar Conformal Maps in CFT
Here are the three theorems about conformal transformations on the complex plane that underpin virtually every construction and constraint in two-dimensional conformal field theory.
1. Local Conformality: Holomorphicity + Non-vanishing Derivative
Any map
\begin{equation}
π:π \subset πΆ \rightarrow πΆ
\end{equation}
is locally angle-preserving (conformal) if and only if it is holomorphic and
\begin{equation}
π'(π§) \ne 0\quad \mbox{for all}\ π§ \in π.
\end{equation}
- This fact identifies the infinitesimal generators of local conformal transformations with the modes of holomorphic vector fields
$\ell_π= -π§^{π+1}\partial_π§$.
- These generators satisfy the classical Witt algebra, whose unique central extension is the Virasoro algebra governing stress-tensor dynamics.
2. Global Classification: Mobius Transformations
Every bijective conformal map of the Riemann sphere
$\hat C =πΆ \cup \{\infty\}$ onto itself is a Mobius transformation:
\begin{equation}
π(π§)= \frac{aπ§+π}{βcπ§+π}\quad\mbox{with}\quad ππ=ππ=1.
\end{equation}
- These six real parameters generate the global conformal group
PSL(2,$\mathbb C$).
- In CFT this yields three holomorphic and three anti-holomorphic zero modes
\begin{equation}
(πΏ_{-1},πΏ_0,πΏ_1) \quad\mbox{and}\quad (πΏ_{-1},πΏ_0,πΏ_1) .
\end{equation}
- Correlation functions of primary fields must transform covariantly under these Mobius maps, fixing their overall functional form up to a few constants.
3. Riemann Mapping Theorem
Any non-empty, simply connected proper domain $D \subset\ne \hat{C}$
can be mapped conformally onto the unit disk $D$.
- In practice this allows us to trade one geometry for another---e.g. the cylinder, upper half-plane, or an
$π$-punctured sphere---without altering local operator product expansions.
- Boundary CFT and finite-temperature setups arise by mapping the disk to the upper half-plane (with real-axis boundary) or to an annulus/cylinder via
\begin{equation}
π€= \frac{πΏ}{2\pi} \ln π§.
\end{equation}
- All local data (central charge, conformal weights) remain invariant under these universal maps.
Beyond These Theorems
Once these three cornerstones are in place, you can dive deeper into:
- The Schwarzian derivative and its vanishing criterion for Mobius maps $(\{π,π§\}=0)$.
- The invariance of the cross-ratio
\begin{equation}
\eta = \frac{(π§_{12}π§_{34})}{(π§_{13}π§_{24})}
\end{equation}
under global conformal moves, which forces any four-point function to be
$πΊ(\eta,\overline{\eta})$.
- The extension to higher-genus surfaces via the uniformization theorem, which places CFT on tori and beyond.
- How quantum anomalies promote the Witt algebra to the Virasoro algebra with central charge $π$, completely controlling modular properties of torus partition functions.
These avenues open up the full power of the conformal bootstrap, modular invariance constraints,
and the rich interplay between CFT and modern number theory.
Afterword: I did my best to represent what Copilot presented to me, but
this interaction with the LLM was less than perfect.