1 unc, stat & or pca extensions for data on manifolds fletcher (principal geodesic anal.) best...
TRANSCRIPT
1
UNC, Stat & OR
PCA Extensions for Data on Manifolds
• Fletcher (Principal Geodesic Anal.)• Best fit of geodesic to data
• Constrained to go through geodesic mean
• Huckemann, Hotz & Munk (Geod. PCA)• Best fit of any geodesic to data
• Jung, Foskey & Marron (Princ. Arc Anal.)• Best fit of any circle to data
(motivated by conformal maps)
2
UNC, Stat & OR
PCA Extensions for Data on Manifolds
3
UNC, Stat & OR
Landmark Based Shape Analysis
Key Step: mod out
• Translation
• Scaling
• Rotation
Result:
Data Objects
points on Manifold ( ~ S2k-
4)
4
UNC, Stat & OR
Principal Nested Spheres Analysis
Main Goal:
Extend Principal Arc Analysis (S2 to Sk)
Jung, Dryden & Marron (2012)
5
UNC, Stat & OR
Principal Nested Spheres Analysis
Top Down Nested (small) spheres
6
UNC, Stat & OR
Principal Nested Spheres Analysis
Main Goal:
Extend Principal Arc Analysis (S2 to Sk)
Jung, Dryden & Marron (2012)
Important Landmark: This Motivated
Backwards PCA
7
UNC, Stat & OR
Principal Nested Spheres Analysis
Replace usual forwards view of PCA
Data PC1 (1-d approx)
PC2 (1-d approx of Data-PC1)
PC1 U PC2 (2-d approx)
PC1 U … U PCr
(r-d approx)
8
UNC, Stat & OR
Principal Nested Spheres Analysis
With a backwards approach to PCA
Data PC1 U … U PCr (r-d approx)
PC1 U … U PC(r-1)
PC1 U PC2 (2-d approx)
PC1 (1-d approx)
9
UNC, Stat & OR
Principal Component Analysis
Euclidean Settings:
Forwards PCA = Backwards PCA
(Pythagorean Theorem,
ANOVA Decomposition)
So Not Interesting
But Very Different in Non-Euclidean Settings
(Backwards is Better !?!)
10
UNC, Stat & OR
Principal Component Analysis
Important Property of PCA:
Nested Series of Approximations
(Often taken for granted)
(Desirable in Non-Euclidean Settings)
11
UNC, Stat & OR
How generally applicable is
Backwards approach to PCA?
Where is this already being done???
An Interesting Question
12
UNC, Stat & OR
How generally applicable is
Backwards approach to PCA?
An Application:
Nonnegative Matrix Factorization
= PCA in Positive Orthant
Think
With ≥ 0 Constraints (on both & )
An Interesting Question
13
UNC, Stat & OR
Standard Approach:
Lee et al (1999):
Formulate & Solve Optimization
Major Challenge:
Not Nested, ()
Nonnegative Matrix Factorization
14
UNC, Stat & OR
Standard NMF
(Projections
All Inside
Orthant)
Nonnegative Matrix Factorization
15
UNC, Stat & OR
Standard NMF
But Note
Not Nested
No “Multi-scale”
Analysis
Possible (Scores Plot?!?)
Nonnegative Matrix Factorization
16
UNC, Stat & OR
Improved Version:
Use Backwards PCA Idea
“Nonnegative Nested Cone
Analysis”
Collaborator:
Lingsong Zhang (Purdue)
Zhang, Marron, Lu (2013)
Nonnegative Matrix Factorization
17
UNC, Stat & OR
Same Toy
Data Set
All
Projections
In Orthant
Nonnegative Nested Cone Analysis
18
UNC, Stat & OR
Same Toy
Data Set
Rank 1
Approx.
Properly
Nested
Nonnegative Nested Cone Analysis
19
UNC, Stat & OR
Chemical
Spectral
Data
Gives
Clearer
View
Nonnegative Nested Cone Analysis
20
UNC, Stat & OR
Chemical
Spectral
Data
Rank 3
Approximation Highlights Lab Early Error
Nonnegative Nested Cone Analysis
21
UNC, Stat & OR
5-d Toy
Example
(Rainbow
Colored
by Peak
Order)
Nonnegative Nested Cone Analysis
22
UNC, Stat & OR
5-d Toy Example Rank 1 NNCA Approx.
Nonnegative Nested Cone Analysis
23
UNC, Stat & OR
5-d Toy Example Rank 2 NNCA Approx.
Nonnegative Nested Cone Analysis
24
UNC, Stat & OR
5-d Toy Example Rank 2 NNCA Approx.
Nonneg.
Basis
Elements
(Not Trivial)
Nonnegative Nested Cone Analysis
25
UNC, Stat & OR
5-d Toy Example Rank 3 NNCA Approx.
Current
Research:
How Many
Nonneg.
Basis El’ts
Needed?
Nonnegative Nested Cone Analysis
26
UNC, Stat & OR
How generally applicable is
Backwards approach to PCA?
Potential Application: Principal Curves
Hastie & Stuetzle, (1989)
(Foundation of Manifold Learning)
An Interesting Question
27
UNC, Stat & OR
Goal: Find lower dimensional manifold that well approximates data
ISOmap
Tennenbaum (2000)
Local Linear Embedding
Roweis & Saul (2000)
Manifold Learning
28
UNC, Stat & OR
1st Principal Curve
Linear Reg’n
Usual Smooth
29
UNC, Stat & OR
1st Principal Curve
Linear Reg’n
Proj’s Reg’n
Usual Smooth
30
UNC, Stat & OR
1st Principal Curve
Linear Reg’n
Proj’s Reg’n
Usual Smooth
Princ’l Curve
31
UNC, Stat & OR
How generally applicable is
Backwards approach to PCA?
Potential Application: Principal Curves
Perceived Major Challenge:
How to find 2nd Principal Curve?
Backwards approach???
An Interesting Question
32
UNC, Stat & OR
Key Component:
Principal Surfaces
LeBlanc & Tibshirani (1996)
An Interesting Question
33
UNC, Stat & OR
Key Component:
Principal Surfaces
LeBlanc & Tibshirani (1996)
Challenge:
Can have any dimensional surface,
But how to nest???
An Interesting Question
34
UNC, Stat & OR
How generally applicable is
Backwards approach to PCA?
Another Potential Application:
Trees as Data
(early days)
An Interesting Question
35
UNC, Stat & OR
How generally applicable is
Backwards approach to PCA?
An Attractive Answer
An Interesting Question
36
UNC, Stat & OR
How generally applicable is
Backwards approach to PCA?
An Attractive Answer:
James Damon, UNC Mathematics
Geometry
Singularity
Theory
An Interesting Question
37
UNC, Stat & OR
How generally applicable is
Backwards approach to PCA?
An Attractive Answer:
James Damon, UNC Mathematics
Damon and Marron (2013)
An Interesting Question
38
UNC, Stat & OR
How generally applicable is
Backwards approach to PCA?
An Attractive Answer:
James Damon, UNC Mathematics
Key Idea: Express Backwards PCA as
Nested Series of Constraints
An Interesting Question
39
UNC, Stat & OR
Define Nested Spaces via Constraints
Satisfying More Constraints
Smaller Subspaces
General View of Backwards PCA
40
UNC, Stat & OR
Define Nested Spaces via Constraints
E.g. SVD
(Singular Value Decomposition =
= Not Mean Centered PCA)
(notationally very clean)
General View of Backwards PCA
41
UNC, Stat & OR
Define Nested Spaces via Constraints
E.g. SVD
Have Nested Subspaces:
General View of Backwards PCA
42
UNC, Stat & OR
Define Nested Spaces via Constraints
E.g. SVD
-th SVD Subspace
Scores
Loading Vectors
General View of Backwards PCA
43
UNC, Stat & OR
Define Nested Spaces via Constraints
E.g. SVD
Now Define:
General View of Backwards PCA
44
UNC, Stat & OR
Define Nested Spaces via Constraints
E.g. SVD
Now Define:
Constraint Gives Nested Reduction of Dim’n
General View of Backwards PCA
45
UNC, Stat & OR
Define Nested Spaces via Constraints
• Backwards PCA
Reduce Using Affine Constraints
General View of Backwards PCA
46
UNC, Stat & OR
Define Nested Spaces via Constraints
• Backwards PCA
• Principal Nested Spheres
Use Affine Constraints (Planar Slices)
In Ambient Space
General View of Backwards PCA
47
UNC, Stat & OR
Define Nested Spaces via Constraints
• Backwards PCA
• Principal Nested Spheres
• Principal Surfaces
Spline Constraint Within Previous?
General View of Backwards PCA
48
UNC, Stat & OR
Define Nested Spaces via Constraints
• Backwards PCA
• Principal Nested Spheres
• Principal Surfaces
Spline Constraint Within Previous?
{Been Done Already???}
General View of Backwards PCA
49
UNC, Stat & OR
Define Nested Spaces via Constraints
• Backwards PCA
• Principal Nested Spheres
• Principal Surfaces
• Other Manifold Data Spaces
Sub-Manifold Constraints??
(Algebraic Geometry)
General View of Backwards PCA
50
UNC, Stat & OR
Define Nested Spaces via Constraints
• Backwards PCA
• Principal Nested Spheres
• Principal Surfaces
• Other Manifold Data Spaces
• Tree Spaces
Suitable Constraints???
General View of Backwards PCA
51
UNC, Stat & OR
New Topic
Curve Registration
52
UNC, Stat & OR
Collaborators
• Anuj Srivastava (Florida State U.)• Wei Wu (Florida State U.)• Derek Tucker (Florida State U.)• Xiaosun Lu (U. N. C.)• Inge Koch (U. Adelaide)• Peter Hoffmann (U. Adelaide)
53
UNC, Stat & OR
Context
Functional Data AnalysisCurves as Data Objects
Toy Example:
54
UNC, Stat & OR
Context
Functional Data AnalysisCurves as Data Objects
Toy Example:
How Can WeUnderstandVariation?
55
UNC, Stat & OR
Context
Functional Data AnalysisCurves as Data Objects
Toy Example:
How Can WeUnderstandVariation?
56
UNC, Stat & OR
Context
Functional Data AnalysisCurves as Data Objects
Toy Example:
How Can WeUnderstandVariation?
57
UNC, Stat & OR
Functional Data Analysis
InsightfulDecomposition
58
UNC, Stat & OR
Functional Data Analysis
InsightfulDecomposition
Horiz’l Var’n
59
UNC, Stat & OR
Functional Data Analysis
InsightfulDecomposition
Vertical Variation
Horiz’l Var’n
60
UNC, Stat & OR
Challenge
Fairly Large Literature
Many (Diverse) Past Attempts
Limited Success (in General)
Surprisingly Slippery
(even mathematical formulation)
61
UNC, Stat & OR
Challenge (Illustrated)
Thanks to Wei Wu
62
UNC, Stat & OR
Challenge (Illustrated)
Thanks to Wei Wu
63
UNC, Stat & OR
Functional Data Analysis
AppropriateMathematicalFramework? Vertical Variation
Horiz’l Var’n
64
UNC, Stat & OR
Landmark Based Shape Analysis
Approach: Identify objects that are:
• Translations
• Rotations
• Scalings
of each other
Mathematics: Equivalence Relation
Results in: Equivalence Classes
Which become the Data Objects
65
UNC, Stat & OR
Landmark Based Shape Analysis
Equivalence Classes become Data Objects
a.k.a. “Orbits”
Mathematics: Called “Quotient Space”
, , , , , ,
66
UNC, Stat & OR
Curve Registration
What are theData Objects?
Vertical Variation
Horiz’l Var’n
67
UNC, Stat & OR
Curve Registration
What are the Data Objects?
Consider “Time Warpings”
(smooth)
More Precisely: Diffeomorphisms
68
UNC, Stat & OR
Curve Registration
Diffeomorphisms
is 1 to 1 is onto
(thus is invertible) Differentiable is Differentiable
69
UNC, Stat & OR
Time Warping Intuition
Elastically Stretch & Compress Axis
70
UNC, Stat & OR
Time Warping Intuition
Elastically Stretch & Compress Axis
(identity)
71
UNC, Stat & OR
Time Warping Intuition
Elastically Stretch & Compress Axis
72
UNC, Stat & OR
Time Warping Intuition
Elastically Stretch & Compress Axis
73
UNC, Stat & OR
Time Warping Intuition
Elastically Stretch & Compress Axis
74
UNC, Stat & OR
Curve Registration
Say curves and are equivalent,
When so that
75
UNC, Stat & OR
Curve Registration
Toy Example: Starting Curve,
76
UNC, Stat & OR
Curve Registration
Toy Example: Equivalent Curves,
77
UNC, Stat & OR
Curve Registration
Toy Example: Warping Functions
78
UNC, Stat & OR
Curve Registration
Toy Example: Non-Equivalent Curves
CannotWarpIntoEach Other
79
UNC, Stat & OR
Data Objects I
Equivalence Classes of Curves
(parallel to Kendall shape analysis)
80
UNC, Stat & OR
Data Objects I
Equivalence Classes of Curves
(Set of AllWarps ofGiven Curve)
Notation: for a “representor”
81
UNC, Stat & OR
Data Objects I
Equivalence Classes of Curves
(Set of AllWarps ofGiven Curve)
Next Task: Find Metric on Equivalence Classes
82
UNC, Stat & OR
Metrics in Curve Space
Find Metric on Equivalence Classes
Start with Warp Invariance on Curves& Extend
83
UNC, Stat & OR
Metrics in Curve Space
Traditional Approach to Curve
Registration:
• Align curves, say and
• By finding optimal time warp, , so:
• Vertical var’n: PCA after alignment
• Horizontal var’n: PCA on s
84
UNC, Stat & OR
Metrics in Curve Space
Problem:
Don’t have proper metric
Since:
Because:
85
UNC, Stat & OR
Metrics in Curve Space
Thanks toXiaosun Lu
86
UNC, Stat & OR
Metrics in Curve Space
Note:VeryDifferentL2 norms
Thanks toXiaosun Lu