LFD Book Forum lecture 8: understanding bias
 User Name Remember Me? Password
 Register FAQ Calendar Mark Forums Read

 Thread Tools Display Modes
#1
02-09-2013, 09:41 AM
 ilya239 Senior Member Join Date: Jul 2012 Posts: 58
lecture 8: understanding bias

The VC dimension is single number that is a property of the hypothesis set.
But, what is "bias of a hypothesis set"? Bias seems to depend also on dataset size and the learning algorithm, since it depends on ; depends on the learning algorithm, and the set of datasets over which the expectation is taken depends on dataset size.

Slide 4 says that bias measures "how well can approximate ". Does this mean "with a sufficiently large dataset and a perfect learning algorithm"?
Is the bias of a (hypothesis set, learning algorithm) combination a single value -- the asymptote of the learning curve? Or is there some notion of bias that is a property of a hypothesis set by itself? If the hypothesis set contains the target function, that does not mean the bias is zero, does it? The beginning of the lecture seems to imply otherwise, but if there is no restriction on the learning algorithm, what guarantees that the average function will in fact be close to the target function for large enough dataset size?
Or is it assumed that the learning algorithm always picks a hypothesis which minimizes ?
#2
02-09-2013, 01:01 PM
 yaser Caltech Join Date: Aug 2009 Location: Pasadena, California, USA Posts: 1,478
Re: lecture 8: understanding bias

Quote:
 Originally Posted by ilya239 The VC dimension is single number that is a property of the hypothesis set. But, what is "bias of a hypothesis set"? Bias seems to depend also on dataset size and the learning algorithm, since it depends on ; depends on the learning algorithm, and the set of datasets over which the expectation is taken depends on dataset size.
Your observation is correct that the bias-variance analysis is not as general as the VC analysis. The bias does depend on the learning algorithm. It also depends on the number of examples, usually slightly.

Quote:
 Slide 4 says that bias measures "how well can approximate ". Does this mean "with a sufficiently large dataset and a perfect learning algorithm"? Is the bias of a (hypothesis set, learning algorithm) combination a single value -- the asymptote of the learning curve? Or is there some notion of bias that is a property of a hypothesis set by itself? If the hypothesis set contains the target function, that does not mean the bias is zero, does it? The beginning of the lecture seems to imply otherwise, but if there is no restriction on the learning algorithm, what guarantees that the average function will in fact be close to the target function for large enough dataset size? Or is it assumed that the learning algorithm always picks a hypothesis which minimizes ?
Good questions . What you are saying would hold if we were using the best approximation of in as the vehicle for measuring the bias. We are not. We are using a "limited resource" version of it that is based on averaging hypotheses that we get from training on a finite set of data points. This version is often close to the best approximation so that's why we can take that liberty.
__________________
Where everyone thinks alike, no one thinks very much
#3
02-09-2013, 02:31 PM
 ilya239 Senior Member Join Date: Jul 2012 Posts: 58
Re: lecture 8: understanding bias

Quote:
 Originally Posted by yaser The bias does depend on the learning algorithm. It also depends on the number of examples, usually slightly. ... This version is often close to the best approximation so that's why we can take that liberty.
Thanks for the explanation.
In HW4 #4 the average hypothesis is measurably shifted from the hypothesis set member giving the lowest mean squared error. Probably because two-point dataset is too small, i.e. this is not representative of realistic cases?
#4
02-09-2013, 06:49 PM
 yaser Caltech Join Date: Aug 2009 Location: Pasadena, California, USA Posts: 1,478
Re: lecture 8: understanding bias

Quote:
 Originally Posted by ilya239 Thanks for the explanation. In HW4 #4 the average hypothesis is measurably shifted from the hypothesis set member giving the lowest mean squared error. Probably because two-point dataset is too small, i.e. this is not representative of realistic cases?
Indeed, the fewer the number of points, the more likely that the average hypothesis will differ from the best approximation. The difference tends to be small, though.
__________________
Where everyone thinks alike, no one thinks very much
#5
02-11-2013, 10:50 AM
 gah44 Invited Guest Join Date: Jul 2012 Location: Seattle, WA Posts: 153
Re: lecture 8: understanding bias

Quote:
 Originally Posted by ilya239 Thanks for the explanation. In HW4 #4 the average hypothesis is measurably shifted from the hypothesis set member giving the lowest mean squared error. Probably because two-point dataset is too small, i.e. this is not representative of realistic cases?
Well, it is also that the two point data set is small relative to the two parameter hypotheses. If you have 100 points, and 99th degree polynomials, it would also have large variance. I will guess that minimizing bias plus variance happens with the number of fit parameters near the square root of the number of points per data set.
#6
02-11-2013, 11:45 AM
 ilya239 Senior Member Join Date: Jul 2012 Posts: 58
Re: lecture 8: understanding bias

Quote:
 Originally Posted by gah44 Well, it is also that the two point data set is small relative to the two parameter hypotheses. If you have 100 points, and 99th degree polynomials, it would also have large variance. I will guess that minimizing bias plus variance happens with the number of fit parameters near the square root of the number of points per data set.
Large variance, sure. I was trying to understand why large bias. If you take a huge number of 100-point datasets, learn a hypothesis from each, and take the average value of these, why might it be far from the target function's value?
On the other hand, I'm not sure how to prove that it won't be far
#7
02-11-2013, 01:04 PM
 yaser Caltech Join Date: Aug 2009 Location: Pasadena, California, USA Posts: 1,478
Re: lecture 8: understanding bias

Quote:
 Originally Posted by ilya239 I was trying to understand why large bias. If you take a huge number of 100-point datasets, learn a hypothesis from each, and take the average value of these, why might it be far from the target function's value? On the other hand, I'm not sure how to prove that it won't be far
It is unlikely (as a practical observation) to be far, but it is likely to be different.
__________________
Where everyone thinks alike, no one thinks very much
#8
02-11-2013, 07:43 PM
 gah44 Invited Guest Join Date: Jul 2012 Location: Seattle, WA Posts: 153
Re: lecture 8: understanding bias

Well, when I wrote that one I was remembering the first time I tried using a polynomial fit program. (It was in Fortran 66, as a hint to how long ago that was.)

I fit an N degree polynomial to N points.

Even so, I believe if you fit a 99th degree polynomials to sets of 100 points you will have a large variance, as did the 1st degree to two points. It won't be easy at all to visualize, though.
#9
02-17-2013, 05:02 PM
 ilya239 Senior Member Join Date: Jul 2012 Posts: 58
Re: lecture 8: understanding bias

Quote:
 Originally Posted by yaser It is unlikely (as a practical observation) to be far, but it is likely to be different.
Sorry to be harping on this question, but I just wanted to ask: is there any intuitive way to see that the average hypothesis will be close to the best hypothesis from the hypothesis set, beyond "practical observation"? E.g. for hypothesis sets satisfying certain well-behavedness criteria, such as being parameterized by a finite number of parameters, containing only continuous functions, etc. The lectures rely in crucial ways on this assumption and it would help to get some more intuition for why it is true for the typically used hypothesis sets, if possible.
#10
02-17-2013, 06:08 PM
 magdon RPI Join Date: Aug 2009 Location: Troy, NY, USA. Posts: 597
Re: lecture 8: understanding bias

In general one cannot say anything analytical about bias and variance. For example the average hypothesis can be very far from the best hypothesis in the model for arbitrarily constructed hypothesis sets and learning algorithms. For example, the average function need not even be in the hypothesis set. However, what we say about the average function being a good approximation to the best you can do is not that far off for general models used in practice.

Problem 4.11 takes you through one of the few situations where one can say something reasonably technical. We can extrapolate (without proof) the conclusions to the more general setting as follows:

(1) When the model is well specified: this means that the hypothesis set contains the target function or a good approximation to it;

(2) When the noise has zero mean and is well behaved, for example having finite variance;

(3) When the learning algorithm is reasonably "stable", which means that small perturbations in the data set lead to small "proportionate" changes in the learned hypothesis (the learning algorithm version of a bounded first derivative);

Then, the average learned function will be approximately the one you would learn from a data set having zero noise; this zero noise hypothesis will (for reasonable N) be close to the optimal function you could learn and will become more so very quickly with increasing N (think trying to learn a polynomial with noiseless data). The conditions above are reasonably general. It is the 3rd condition that is most important, and one can mostly relax the well specified requirement in practice.

Quote:
 Originally Posted by ilya239 Sorry to be harping on this question, but I just wanted to ask: is there any intuitive way to see that the average hypothesis will be close to the best hypothesis from the hypothesis set, beyond "practical observation"? E.g. for hypothesis sets satisfying certain well-behavedness criteria, such as being parameterized by a finite number of parameters, containing only continuous functions, etc. The lectures rely in crucial ways on this assumption and it would help to get some more intuition for why it is true for the typically used hypothesis sets, if possible.
__________________
Have faith in probability

 Tags bias, lecture 8

 Thread Tools Display Modes Linear Mode

 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 Rules
 Forum Jump User Control Panel Private Messages Subscriptions Who's Online Search Forums Forums Home General     General Discussion of Machine Learning     Free Additional Material         Dynamic e-Chapters         Dynamic e-Appendices Course Discussions     Online LFD course         General comments on the course         Homework 1         Homework 2         Homework 3         Homework 4         Homework 5         Homework 6         Homework 7         Homework 8         The Final         Create New Homework Problems Book Feedback - Learning From Data     General comments on the book     Chapter 1 - The Learning Problem     Chapter 2 - Training versus Testing     Chapter 3 - The Linear Model     Chapter 4 - Overfitting     Chapter 5 - Three Learning Principles     e-Chapter 6 - Similarity Based Methods     e-Chapter 7 - Neural Networks     e-Chapter 8 - Support Vector Machines     e-Chapter 9 - Learning Aides     Appendix and Notation     e-Appendices

All times are GMT -7. The time now is 10:51 PM.

 Contact Us - LFD Book - Top