Frame, Reproducing Kernel and Learning - PowerPoint PPT Presentation

1 / 26
About This Presentation
Title:

Frame, Reproducing Kernel and Learning

Description:

St phane Canu. http://asi.insa-rouen.fr/~arakotom. Alain.Rakoto,Stephane.Canu_at_insa-rouen.fr ... Wavelet-based approximation (wavelet or ridgelet networks) are ... – PowerPoint PPT presentation

Number of Views:118
Avg rating:3.0/5.0
Slides: 27
Provided by: asiIns
Category:

less

Transcript and Presenter's Notes

Title: Frame, Reproducing Kernel and Learning


1
Frame, Reproducing Kernel and Learning
  • Alain Rakotomamonjy
  • Stéphane Canu

Perception, Systèmes et Information Insa de
Rouen, 76801 St Etienne du Rouvray France
Alain.Rakoto,Stephane.Canu_at_insa-rouen.fr
http//asi.insa-rouen.fr/arakotom
2
Motivations
  • Wavelet-based approximation (wavelet or ridgelet
    networks) are regularization networks?
  • Construction of multiresolution scheme of
    approximation
  • kernel adapted to the structures of function to
    be learned

3
Motivations Ctd.
  • Frame based framework for learning

Approximating highly oscillating structure
Without losing regularity in smooth region
4
Road Map
  • Introduction on Frame
  • From Frame to Kernels
  • From Frame kernels to learning
  • Conclusions and perspectives

5
Frame A definition
  • H Hilbert Space dot product

A sequence of elements of H
is a frame of H if there exists A,B gt O s.t
A,B are the frame bounds
6
Frame definition Ctd.
  • Frame intepretation
  • Frame allows stable representation
  • as for all f in H

Frame "Basis" linear dependency redundancy
being a dual frame of Fn in H
7
Particular cases of Frame
  • Tight Frame
  • Frame with bounds s.t AB
  • Orthonormal Basis
  • AB1
  • Riesz Basis
  • Frame elements are linearly independent

8
Examples of Frame
  • Tight Frame of IR2
  • Frame of L2(IR)

F2
F1
F3
Y is an admissible wavelet
9
Road Map
  • Introduction on Frame
  • From Frame to Kernels
  • From Frame kernels to learning
  • Conclusions and perspectives

10
Frameable RKHS
  • Condition for having a RKHS

Suppose H is a Hilbert space of function
and a frame of H
H is a RKHS if
On a frameable Hilbert Space, this is equivalent
to
The Reproducing Kernel is
11
Construction of Frameable RKHS
  • A Practical way to build a RKHS
  • F is a Hilbert Space of function

A finite set of F elements such that
?
?
is a RKHS with Fn as frame elements
12
Example of Frameable RKHS
  • frameable RKHS included in L2(IR)

Fi L2 function (e.g Fi is a wavelet) span
Fii1N is a RKHS
Example
3 wavelets at same scale j
span a RKHS with kernel
13
Road Map
  • Introduction on Frame
  • From Frame to Kernels
  • From Frame kernels to learning
  • Conclusions and perspectives

14
Semiparametric Estimation
  • Context

Learning from training set (xi,yi)i1..N
Semiparametric framework
One looks for the minimizer of the risk functional
in a space H spanYii1m H being a RKHS
Under general conditions,
spanYii1m parametric hypothesis space
15
Semiparametric Estimation
  • Parametric hyp. space is a frameable RKHS

P is a frameable RKHS spanned by Fn, with P ?
H, H RHKS
Semiparametric estimation on H with P as a
parametric hyp. space
One looks for the minimizer in H of
As spaces are orthogonal, backfitting is
sufficient for estimating f
16
Semiparametric Estimation
  • Frame view point
  • H frameable
  • H defined by kernel K

H P N
P Frameable RKHS, N Frameable RKHS
H
N "unknown component" to be regularized
P ? N due to linear dependency of frame
P "known component" not to regularized
KNKH-KP
P Frameable RKHS
17
Multiscale approximation
  • H a frameable RKHS

H is splitted in different spaces Fii1m-1 and
H0
And any space Hi or Fi is a RKHS
Hi Trend Spaces
Fi Details Spaces
18
Multiscale Approximation Ctd.
At each step j, trend obtained at step j-1 is
decomposed in trend and details
H
H2
F2
H1
F1
H0
F0
19
Multiscale Approximation Ctd.
  • Validity
  • At each step, representer Theorem Hypothesis must
    be verified
  • Solution

20
Illustration on toy problem
Function to be learned
Data
xi N points from the random sampling of 0, 10

Algorithm
- SVM Regression
- Multiscale Regularisation networks on Frameable
RKHS
Sin/Sinc based kernel
Wavelet based kernel
21
Results
  • N902
  • Results are averagerad over 300 experiments and
    normalized with regards to SVM performance

Wavelet Kernel
Sinc Kernel
SVM
1 0.096
0.9297 0.312
0.5115 0.098
L2 error
0.7252 8.022
0.8280 0.025
1 0.028
22
Plots of typical results
23
Road Map
  • Introduction on Frame
  • From Frame to Kernels
  • From Frame kernels to learning
  • Conclusions and perspectives

24
Summary
  • new design of kernel based on frame elements
  • algorithm for multiscale learning
  • But
  • no explicit definition of kernel
  • Time-consuming

25
Future work
  • Multidimensional extension
  • Tight Frame of multidimensional wavelet
  • Using a priori knowledge on the learning problem
  • How to choose the frame elements?
  • Theoretical justification and analysis of
    multiscale approximation

26
(No Transcript)
Write a Comment
User Comments (0)
About PowerShow.com