supervised sparse and functional principal …...supervised sparse and functional principal...
TRANSCRIPT
Supervised Sparse and Functional Principal Component Analysis
Li et al. (2015)
December 1, 2015
Supervised Sparse and Functional Principal Component Analysis 1
Topics
• functional PCA
•
Supervised Sparse and Functional Principal Component Analysis 2
Functional FPCA
0 100 200 300
0.02
0.03
0.04
0.05
0.06
0.07
1th PC: 89.161
valu
es
0 100 200 300−
0.05
0.00
0.05
2th PC: 8.436
valu
es
0 100 200 300
−0.
050.
000.
05
3th PC: 1.8
valu
es
0 100 200 300
−0.
050.
000.
050.
10
4th PC: 0.442
valu
es
• 35 cities(curves)
• 365 days of temperature measured
0 100 200 300
−30
−20
−10
010
20
days
tem
pSupervised Sparse and Functional Principal Component Analysis 3
Consider another data•
Supervised Sparse and Functional Principal Component Analysis 4
Consider another data
• patient arrival rate data (hourly)
• 417 consecutive days
• shall we perform FPCA using all thedata together? Could they be consideredas replicates?
• what we might lose if we analysis themseparately?
• we we might gain if we combine them?
Supervised Sparse and Functional Principal Component Analysis 5
The Main Problem: Row-rank model
• Xi (s) = Zi (s) + ei (s): functional data for (i)th sample
• rank-r functional PCA model:
Zi (s) = µ(s) +r∑
k=1
uikVk(s) = µ(s) + uT(i)V(s)
• u(i)(r × 1) score vector for (i) th sample
• V(s): collection of r loading functions
• uT(i)V(s): low rank approximation of the (i)th demeaned Xi (s)− µ(s)
Supervised Sparse and Functional Principal Component Analysis 6
SupSFPC model• Xi (s) = Zi (s) + ei (s): functional data for (i)th sample
• rank-r functional PCA model:
Zi (s) = µ(s) +r∑
k=1
uikVk(s) = µ(s) + uT(i)V(s)
• y(i)(q × 1): supervision set; extra information available for the ith sample;high-dimensional
u(i) = β0 + BTy(i) + f(i)
• multivariate linear model
• β0(r × 1);B(q × r); f(i) ∼ MVN(0,Σf)
• β0 + BTy(i) variation in u(i) explained by y(i)• fbold(i) left over variation
Supervised Sparse and Functional Principal Component Analysis 7
Combining Rank-r model with SupSFPC Model• Xi (s) = Zi (s) + ei (s)
• rank-r functional PCA model:
Zi (s) = µ(s) + uT(i)V(s)
• SupSFPC Model:u(i) = β0 + BTy(i) + f(i)
•Xi (s) = [µ(s) + βT
0 V(s)] + yT(i)BV(s) + [f(i)V(s) + ei (s)]
• [µ(s) + βT0 V(s)] intercept;
• yT(i)BV(s) fixed term
• [f(i)V(s) + ei (s)] random term
• Primary Interest: yT(i)BV(s) + f(i)V(s)
Supervised Sparse and Functional Principal Component Analysis 8
Other Assumptions
• SupSFPC Model:
Xi (s) = [µ(s) + βT0 V(s)] + yT(i)BV(s) + [f(i)V(s) + ei (s)]
• Primary Interest: yT(i)BV(s) + f(i)V(s)
• B and V(s) are potentially sparse
• B selection of important features in y
• V (s): the support 6= the entire domain S
Supervised Sparse and Functional Principal Component Analysis 9
What Li et al. (2015) is trying to do?
• estimating variation within X (s): V(s)
• by incorporating the information of y
• select important features in y that are most likely to drive the low-rank structure of X (s)
• allowing V(s) to by sparse and smooth
Supervised Sparse and Functional Principal Component Analysis 10
Revisit the Hospital rate data(no featureselection)V(s) yT(i)BV(s)
Supervised Sparse and Functional Principal Component Analysis 11
Application II (with feature selection)
• X (t): 542 genes (every 7 mins; 18 timepoints)
• y: ChiP-chip data (106 TFs)• Goal 1: understanding the underlying
expression patterns of cell cycle-relatedgenes
• Goal 2: identifying transcription factors(TFs) that regulate cell cycles
Supervised Sparse and Functional Principal Component Analysis 12
Goal 1: understanding the underlyingexpression patterns
Supervised Sparse and Functional Principal Component Analysis 13
Goal 2: identifying transcriptionfactors (TFs) that regulate cell cycles32 out of 106 TFs are selected
Supervised Sparse and Functional Principal Component Analysis 14
Estimation Details
Xi (s) = yT(i)BV(s) + [f(i)V(s) + ei (s)]
X = YBVT + FVT + E
• n sample size; p time points; r # of FPCs
• X (n × p); V (p × r); E (n × p); F (n × r)
•x(i) ∼ MVN(yT(i)BV,V
TΣfVT + σ2eI)
• Likelihood:
L(X) = −np
2log(2π)− n
2log det(VTΣfV
T + σ2eIp)
− 1
2Tr((X− YBVT )(VTΣfV
T + σ2eIp)(X− YBVT )T )
Supervised Sparse and Functional Principal Component Analysis 15
Imposing sparse and smooth structure
X = YBVT + FVT + E
• Likelihood:
L(X) = −np
2log(2π)− n
2log det(VTΣfV
T + σ2eIp)
− 1
2Tr((X− YBVT )(VTΣfV
T + σ2eIp)(X− YBVT )T )
•maxθL(X)− Pf (V)− Ps(V)− Ps(B)
• Pf (V) =∑r
k=1 αkvTk Ωvk roughness penalty
• Ps(V) =∑r
k=1 λk ||vk ||1,Ps(B) =∑r
k=1 γk ||bk ||1 sparsity
• EM algorithm
Supervised Sparse and Functional Principal Component Analysis 16
Identifiability
X = YBVT + FVT + E
• Q r × r orthogonal
• BVT = BQQTVT , FVT = FQQTVT
• (1)∫Vi (s)Vj(s)ds = 0 or 1
• (2) Σf is diagonal with distinct positive eigenvalues
• (3) diagonal of Σf are strictly decreasing
• Challenge is to minimize L(X) under these constraints
Supervised Sparse and Functional Principal Component Analysis 17
Challenges in Computing
L(X) = −np
2log(2π)− n
2log det(VTΣfV
T + σ2eIp)
− 1
2Tr((X− YBVT )(VTΣfV
T + σ2eIp)(X− YBVT )T )
• non-differentiable for the sparsity penalties
• non-convex feasible region determined by identifiability constraints
• V shared by the mean and the covariance terms
Supervised Sparse and Functional Principal Component Analysis 18
EM algorithm
X = YBVT + FVT + E
X = UVT + E
U = YB + F
• L(X,U) = L(X|U) + L(U)
• L(X|U) ≈ −np log σ2e − σ−2e Tr
[(X−UVT )(X −UVT )T
]• L(U) ≈ −n log det Σf − Tr
[(U− YB)Σ−1
f (U− YB)T ]
Supervised Sparse and Functional Principal Component Analysis 19
EM algorithm
X = UVT + E
U = YB + F
• L(X,U) = L(X|U) + L(U)
• L(X|U) depends on σ2e ,V
• L(U) depends on B,Y
Supervised Sparse and Functional Principal Component Analysis 20
EM algorithm
X = UVT + E U = YB + F
Supervised Sparse and Functional Principal Component Analysis 21
Estimation of V
• Challenge: the orthogonality constraints of V
• Optimizing one column by one column of V
• a block coordinate decent algorithm
• eventually the orthogonality is maintained (simulation 85, yeast cell data, 87.7)
Supervised Sparse and Functional Principal Component Analysis 22
Reference
Gen Li, Haipeng Shen, and Jianhua Z Huang. Supervisedsparse and functional principal component analysis.
Journal of Computational and Graphical Statistics,(just-accepted):00, 2015.
Supervised Sparse and Functional Principal Component Analysis 23