MHB Master algorithm design and upper bound proof

AI Thread Summary
The discussion revolves around a user seeking help with a past exam question related to online learning. The user has made some initial progress by establishing a loss function for a binary classification scenario, represented as Loss(S) = ∑|yt - ŷt|. However, they express uncertainty about how to advance from this point. Other participants emphasize the importance of sharing progress to facilitate better assistance, encouraging the user to provide more details about their thought process or any attempts made to solve the problem. This collaborative approach aims to enhance the effectiveness of the help provided.
akerman
Messages
26
Reaction score
0
Hello,

I am currently preparing myself for exams and I have a past exam question which I can't solve. This question concerns online learning and the following picture illustrates it: View attachment 5486
Is anyone able to help me out and propose a solution to this question?
 

Attachments

  • question.JPG
    question.JPG
    99.2 KB · Views: 90
Technology news on Phys.org
Hello, akerman! :D

We ask that our users show their progress (work thus far or thoughts on how to begin) when posting questions. This way our helpers can see where you are stuck or may be going astray and will be able to post the best help possible without potentially making a suggestion which you have already tried, which would waste your time and that of the helper.

Can you post what you have done so far?
 
All I have right now is the initial setting where we do not have k classes but we just use {0,1}. For this setting I have that the mistakes or loss for S (online sequence of data) is:
$Loss(S) = \sum_{t=1}^{m} |y_{t} - \hat{y_{t}} |$

From there I don't know how to progress or solve this question...
 

Thread 'Learning Assembly and computer architecture for x86'

Dear Peeps I have posted a few questions about programing on this sectio of the PF forum. I want to ask you veterans how you folks learn program in assembly and about computer architecture for the x86 family. In addition to finish learning C, I am also reading the book From bits to Gates to C and Beyond. In the book, it uses the mini LC3 assembly language. I also have books on assembly programming and computer architecture. The few famous ones i have are Computer Organization and...
View full post »

Thread 'Learning data structures and algorithms in different programming languages'

I have a quick questions. I am going through a book on C programming on my own. Afterwards, I plan to go through something call data structures and algorithms on my own also in C. I also need to learn C++, Matlab and for personal interest Haskell. For the two topic of data structures and algorithms, I understand there are standard ones across all programming languages. After learning it through C, what would be the biggest issue when trying to implement the same data...
View full post »

Similar threads

Can an O(n) algorithm's actual growth rate exceed n?
Replies
15
Views
2K
MHB Upper Bound of Sets and Sequences: Analyzing Logic
Replies
3
Views
5K
MHB What Type of Math is Used in Fortune's Algorithm?
Replies
1
Views
2K
Least Upper Bound Property ⇒ Archimedean Principle
Replies
1
Views
2K
Upper & Lower Bounds Real Zeros-Polynomial Division, Proofs?
Replies
4
Views
3K
Justification for upper bound in Taylor polynomial
Replies
3
Views
1K
MHB Why is \( c'' \) an Upper Bound for \( U \cap [a, b] \) in Theorem 3.47?
Replies
2
Views
1K
Engineering Plastic Analysis: Upper Bound Theorem
Replies
2
Views
2K
MHB What Is the Upper Bound of Groups of Order in Finite Group Theory?
Replies
2
Views
2K
Fast pentadiagonal matrix solver
Replies
1
Views
3K

Hot Threads

Recent Insights

Back
Top