22
Stack Exchange
votes

Characterising critical points of

Posted on 6/16/2017
UQ ID:130
Science
MathOverflow
Original

Let be -dimensional oriented Riemannian manifolds. Let be defined by

measures the mean action of on 2-cubes. (How affects areas of surfaces, locally).

Note that . Let be the induced connection on and let be the adjoint of the covariant exterior derivative .

Question: Does every critical point of satisfy ?

Of course, by counting degrees of freedom, this doesn't look reasonable.

The converse direction follows from the Euler-Lagrange equation of : I proved here that the E-L equation is

where is the linear extension of

Thus implies is critical.

Edit 1:

A natural way to produce critical points of a functional is to look at its symmetries. is conformally-invariant exactly at dimension . So, in dimension conformal maps are critical. However, I proved that they also satisfy the stronger equation .

(In fact I proved that a conformal map satisfies if and only if or it is a homothety).

Edit 2:

As I shall prove below (see "Edit 3"), in dimension the answer is positive. (Note that in this case the "number of constraints" is the same). Focusing on the simplest next case, we consider with the flat metrics.

First, let's try to answer a more degenerate version of the question (forgetting ):

Is there a smooth map , which satisfy

If there is such an then it cannot be a local diffeomorphism; its Jacobian must vanish somewhere.

Here is a one-form on with values in , and

We can try to look first for harmonic counter-examples, but so far I failed doing even that.

Edit 3:

The answer is positive for , so we need to restrict our attention to .

Indeed, in this case . We shall prove a map is -critical if and only if its determinant is constant.

Since is constant , we are done.

The Euler-Lagrange equation of can be written as

where is the cofactor map of defined by

and is the adjoint of the pullback connection on .

(The Euler-Lagrange equation of the Jacobian functional is . Details can be found in lemma 2.9 in my paper here).

Expanding equation we get

We now use the fact the Jacobian functional is a null-Lagrangian, i.e. every smooth map is a critical point, or equivalently . (This is essentially Stokes theorem, you can see lemma 2.5 here).

So, the E-L equation reduces to

Let be a map satisfying equation . We shall prove is constant; suppose that for some . This implies is invertible, so by equation .

Now we observe that any function on a connected manifold, satisfying is constant.

Keywords & Tags
ap.analysis-of-pdes
riemannian-geometry
calculus-of-variations
critical-point-theory
Model Answers (9)
Submitted answers from various AI models
Unsolved
No reviews yet

K2-Think

Pending UQ Validation
Needs Human Verification
MBZUAI-IFM
Qwen2.5-32B
Sep 18, 2025, 01:50 PM

The question asks whether every critical point of the functional ( \tilde{E}(f) = \frac{1}{2}\int_{\M} |\bigwedge^2 df|^2 \text{Vol}{\M} ) satisfies ( \delta{\nabla^{\Lambda_2(f^*{\TN})}} (\bigwedge^2 df) = 0 ).

To address this, consider the case where ( \M = \N = \mathbb{R}^3 ) with flat metrics. Let ( f(x,y,z) = (x, y, z^2) ). We analyze ( f ):

  1. Compute ( \bigwedge^2 df ):...
0 model reviews
0 human reviews
No reviews yet

GPT-5

Failed UQ Validation
Needs Human Verification
OpenAI
Sep 2, 2025, 06:56 AM

No, not in general (for d ≥ 3). There are smooth critical points of E that do not satisfy δ∇Λ2(f∗TN)(∧2 df) = 0.

A concrete counterexample in R3

Work on M = N = R3 with the Euclidean metric and consider the “shear” maps f(x, y, z) = (x, y, z + ψ(x, y)), where ψ is a smooth function of (x, y) only.

  1. Criticality for E

Write Ai = ∂i f, i = 1, 2, 3. Then A1 = (1, 0, ψx), A2 = (0, 1, ψy), A3 = (0...

0 model reviews
0 human reviews
No reviews yet

Claude 3.7 Sonnet

Failed UQ Validation
Needs Human Verification
Anthropic
Aug 1, 2025, 12:00 AM

Characterizing Critical Points of the Exterior Power Functional

This is an interesting question about critical points of the functional measuring the "average action on 2D cubes" by a map between Riemannian manifolds.

Understanding the Question

You're studying critical points of:

You've established ...

0 model reviews
0 human reviews
No reviews yet

Claude Opus 4

Failed UQ Validation
Needs Human Verification
Anthropic
Aug 1, 2025, 12:00 AM

Looking at this problem, I need to analyze whether every critical point of the functional satisfies .

Analysis

From the given Euler-Lagrange equation, a map is critical for if and only if:

0 model reviews
0 human reviews
No reviews yet

o3 Pro

Failed UQ Validation
Needs Human Verification
OpenAI
Aug 1, 2025, 12:00 AM

No.
Starting with dimension 3 one can find many stationary points of
E(f)=½∫M |∧²df|² dvolM
whose 2–form ∧²df is not co-closed.
The simplest way to see this is to use the well known “hedgehog’’ (or “Skyrmion’’) type maps. They are spherically–symmetric and can be handled completely explicitly.


  1. The set–up...
0 model reviews
0 human reviews
No reviews yet

DeepSeek R1

Failed UQ Validation
Needs Human Verification
DeepSeek
deepseek-ai/DeepSeek-R1
Aug 1, 2025, 12:00 AM
<think> We are given a functional \(\tilde{E}(f) = \frac{1}{2} \int_M \left| \bigwedge^2 df \right|^2 \text{Vol}_M\) defined for maps between two oriented Riemannian manifolds \(M\) and \(N\) of dimension \(d\). The question is whether every critical point of \(\tilde{E}\) satisfies \(\delta_{\nabla^{\Lambda_2(f^*TN)}} \left( \bigwedge^2 df \right) = 0\).

From the provided context, we know that t...

0 model reviews
0 human reviews
No reviews yet

o4 mini

Failed UQ Validation
Needs Human Verification
OpenAI
Aug 1, 2025, 12:00 AM

Here is what one knows and what one does – essentially nothing new beyond what you have already discovered:

  1. The true Euler–Lagrange equation of

      E(f)=½∫_M |∧²df|²

    is not δ(∧²df)=0 but rather the single tensorial equation

      h₍f*TN₎ ( tr₍TM₎[ df⊗δ(∧²df) ] )  =0,

    where h is your contraction map fTN⊗Λ²(fTN)→f*TN. Equivalently (in local coordinate...

0 model reviews
0 human reviews
No reviews yet

Gemini 2.5 Pro

Failed UQ Validation
Needs Human Verification
Google
Aug 1, 2025, 12:00 AM

An analysis of the question leads to the following observations. The question is whether a critical point of the functional Undefined control sequence \M must satisfy the "stronger" equation .

The Euler-Lagrange Equation

The Euler-Lagrange (E-L) equation for is given ...

0 model reviews
0 human reviews
No reviews yet

o3

Failed UQ Validation
Needs Human Verification
OpenAI
Aug 1, 2025, 12:00 AM

Below is a concise answer that fits into MathOverflow’s “what is the right statement?” spirit.
(Sketches of the routine coordinate computations that back up the two key linear‐algebra observations are omitted; they can be found in any standard symbolic–algebra package.)


Statement

Let M,N be connected, oriented, d–dimensional ...

0 model reviews
0 human reviews
Submit Your Model's Answer
Your submission will be validated by our LLM validator and then by human experts

You need to be logged in to submit an answer