LFD Book Forum  

Go Back   LFD Book Forum > Book Feedback - Learning From Data > Chapter 4 - Overfitting

 
 
Thread Tools Display Modes
Prev Previous Post   Next Post Next
  #1  
Old 12-18-2012, 05:00 PM
jk.aero jk.aero is offline
Junior Member
 
Join Date: Jul 2012
Posts: 1
Default Deterministic Noise & Gibb's Phenomenon/Godunov's Theorem

I think deterministic noise represents the error when a higher order 'polynomial' is attempting to model/forecast a much higher order target function. This error reduces when the order of the hypothesis polynomial is reduced. Also, this is indistinguishable from stochastic noise.

I find this similar to Gibb's phenomenon and Godunov's Theorem. Specifically, in Computational Fluid Dynamics, one is required to use a lower (first order) representation near a discontinuity (shock wave) else, the scheme becomes unstable with the magnitude of oscillations near and across the discontinuity (the deterministic noise in this case) growing with every iteration. To address this, limiters are used. Godunov's Theorem states that: "Linear numerical schemes for solving partial differential equations (PDE's), having the property of not generating new extrema (monotone scheme), can be at most first-order accurate."

I just wanted to know if my understanding of deterministic noise and its similarity to Gibb's phenomenon/Godunov's Theorem is correct? If so, are concepts such as limiters, of any use in formulating hypotheses in Machine Learning?
Reply With Quote
 

Tags
deterministic noise, gibb's, godunov, limiters

Thread Tools
Display Modes

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off

Forum Jump


All times are GMT -7. The time now is 02:29 PM.


Powered by vBulletin® Version 3.8.3
Copyright ©2000 - 2019, Jelsoft Enterprises Ltd.
The contents of this forum are to be used ONLY by readers of the Learning From Data book by Yaser S. Abu-Mostafa, Malik Magdon-Ismail, and Hsuan-Tien Lin, and participants in the Learning From Data MOOC by Yaser S. Abu-Mostafa. No part of these contents is to be communicated or made accessible to ANY other person or entity.