Nonparametric%20Divergence%20Estimators%20for%20Independent%20Subspace%20Analysis - PowerPoint PPT Presentation

About This Presentation
Title:

Nonparametric%20Divergence%20Estimators%20for%20Independent%20Subspace%20Analysis

Description:

Title: Conditional Chow-Liu Tree Structures for Modeling Discrete-Valued Vector Time Series Author: Sergey Kirshner Last modified by: Barnabas Created Date – PowerPoint PPT presentation

Number of Views:100
Avg rating:3.0/5.0

less

Transcript and Presenter's Notes

Title: Nonparametric%20Divergence%20Estimators%20for%20Independent%20Subspace%20Analysis


1
Nonparametric Divergence Estimators for
Independent Subspace Analysis
  • Barnabás Póczos (Carnegie Mellon University, USA)
  • Zoltán Szabó (Eötvös Loránd University, Hungary)
  • Jeff Schneider (Carnegie Mellon University, USA)

EUSIPCO-2011 Barcelona, Spain Sept 2, 2011
2
Outline
  • Goal divergence estimation
  • Definitions, basic properties, motivation
  • The estimator
  • Theoretical results
  • Consistency
  • Experimental results
  • Mutual information estimation
  • Independent subspace analysis
  • Low-dimensional embedding of distributions

3
Measuring divergences
Manchester United 07/08
Owen Hargreaves
Cristiano Ronaldo
Rio Ferdinand
KL
Tsallis
Rényi
www.juhokim.com/projects.php
4
How should we estimate them?
  • Naïve plug-in approach using density estimation
  • density estimators
  • histogram
  • kernel density estimation
  • k-nearest neighbors D. Loftsgaarden C.
    Quesenberry. 1965.
  • How can we estimate them directly?

5
kNN density estimation
How good is this estimation?
D. Loftsgaarden and C. Quesenberry. 1965.
N. Leonenko et. al. 2008
6
Divergence Estimation
6
7
Asymptotically unbiased
The estimator
We need to prove
Agner Krarup Erlang
1-?, and ?-1 moments of the normalized k-NN
distances
Normalized k-NN distances converge to the Erlang
distribution
7
8
Asymptotically unbiased
If we could move the limit inside the expectation
All we need is
9
A little problem
Increases the paper length by another 20 pages
10
Results for divergence estimation
2D Normal
10
11
Results for MI estimation
rotated uniform distribution
12
Independent Subspace Analysis
Independent subspaces
6 by 6 mixing matrix
Observation XAS
Estimate A and S observing samples from X only
Goal
12
13
Independent Subspace Analysis
Objective
13
14
Low dimensional embeddig of digits
Noisy USPS datasets
15
Embedding using raw image data
16
Embedding using Rényi divergences
17
Be careful, some mistakes are easy to make
We want
HellyBray theorem
Annals of Statistics
18
Some mistakes
We want
Enough
19
Takeaways
If you need to estimate divergences, then use me!
  • Consistent divergence estimator
  • Direct no need to estimate densities
  • Simple it needs only kNN based statistics
  • Can be used for mutual information estimation,
    independent subspace analysis, low-dimensional
    embedding

Thanks for your attention! ?
20
Attic
Write a Comment
User Comments (0)
About PowerShow.com