Rudin Semicontinuity Exercise

  • Thread starter Tedjn
  • Start date
  • Tags
    Exercise
In summary, the lower semicontinuity of f is key to proving that gn(x) approaches f(x) as n approaches infinity in this problem. By using the lower semicontinuity to construct a sequence of points in X, we can show that gn(x) gets closer and closer to f(x) as n approaches infinity.
  • #1
Tedjn
737
0

Homework Statement



This is #22 of Chapter 2 in Rudin's Real and Complex Analysis 3rd Ed.

Suppose that X is a metric space, with metric d, and that f : X -> [0,infinity] is lower semicontinuous, f(p) < infinity for at least one p in X. For n = 1,2,3,..., x in X, define

[tex]g_n(x) = \inf\,\{\,f(p) + nd(x,p)\,:\,p \in X\,\}[/tex]

and prove that

(i) |gn(x) - gn(y)| <= nd(x,y),
(ii) 0 <= g1 <= g2 <= ... <= f,
(iii) gn(x) -> f(x) as n -> infinity, for all x in X.

Homework Equations



f is lower semicontinuous if for every real a, f-1((a,infinity]) is open in X.

The Attempt at a Solution



This was a from a homework problem due in class earlier today, that just killed me to think about. (i) and (ii) were straightforward, and then I just could not figure out how to show that sup gn = f. Because gn is defined as an inf, what is stopping each subsequent gn from increasing very very little? Perhaps the lower semicontinuity of f, which wasn't necessary for (i) or (ii)? Any help would be appreciated.
 
Physics news on Phys.org
  • #2


Hi there,

Thank you for sharing your thoughts on this problem. It seems like you have made some progress on parts (i) and (ii), which is great! To address your concern about part (iii), you are correct in thinking that the lower semicontinuity of f is key. In order to show that gn(x) approaches f(x) as n approaches infinity, we need to show that for any given x in X and any given epsilon > 0, there exists an n0 such that for all n >= n0, we have |gn(x) - f(x)| < epsilon.

To do this, we can use the lower semicontinuity of f to construct a sequence of points in X that approach x and have f-values that get closer and closer to f(x). Specifically, for each n, we can choose a point pn in X such that f(pn) <= gn(x) + epsilon/2n. Then, we can show that the sequence pn approaches x and that f(pn) approaches f(x) as n approaches infinity. This will give us the desired result.

I hope this helps! Let me know if you have any further questions or if you would like me to elaborate on any part of the solution. Keep up the good work!
 

1. What is the definition of Rudin semicontinuity?

Rudin semicontinuity is a concept in mathematical analysis that describes the behavior of a function at a point relative to the behavior of the function at nearby points. A function is Rudin semicontinuous at a point if the limit of the function at that point is greater than or equal to the infimum of the limits of the function at nearby points.

2. How do you prove Rudin semicontinuity for a function?

To prove Rudin semicontinuity for a function, you must show that the limit at a point is greater than or equal to the infimum of the limits at nearby points. This can be done by using the epsilon-delta definition of limits and carefully choosing the appropriate delta for each nearby point.

3. What is the importance of Rudin semicontinuity in mathematical analysis?

Rudin semicontinuity is important in mathematical analysis because it allows us to study the behavior of a function at a point without knowing the values of the function at that point. This concept is especially useful in studying optimization and minimization problems in calculus and economics.

4. How is Rudin semicontinuity related to continuity?

Rudin semicontinuity is a weaker form of continuity. A function that is continuous at a point is also Rudin semicontinuous at that point. However, a function can be Rudin semicontinuous at a point without being continuous at that point.

5. Can Rudin semicontinuity be generalized to higher dimensions?

Yes, Rudin semicontinuity can be extended to functions of several variables. In this case, the limit at a point must be greater than or equal to the infimum of the limits at nearby points in each of the variables. This concept is important in the study of multivariate calculus and optimization problems in higher dimensions.

Similar threads

  • Calculus and Beyond Homework Help
Replies
2
Views
597
  • Calculus and Beyond Homework Help
Replies
11
Views
1K
  • Calculus and Beyond Homework Help
Replies
9
Views
1K
  • Calculus and Beyond Homework Help
Replies
1
Views
1K
  • Calculus and Beyond Homework Help
Replies
13
Views
1K
  • Calculus and Beyond Homework Help
Replies
2
Views
1K
  • Calculus and Beyond Homework Help
Replies
4
Views
2K
  • Calculus and Beyond Homework Help
Replies
9
Views
7K
  • Calculus and Beyond Homework Help
Replies
1
Views
736
Back
Top