stay on path pca along graph paths
play

Stay on path: PCA along graph paths Megasthenis Asteris - PowerPoint PPT Presentation

Stay on path: PCA along graph paths Megasthenis Asteris Electrical and Computer Engineering Anastasios Kyrillidis Alexandros Dimakis Han - Gyol Yi Communication Sciences and Disorders Bharath Chandrasekaran Sparse PCA Direction of x


  1. Stay on path: 
 PCA along graph paths Megasthenis Asteris Electrical and Computer Engineering Anastasios Kyrillidis Alexandros Dimakis Han - Gyol Yi Communication Sciences and Disorders Bharath Chandrasekaran

  2. Sparse PCA Direction of 
 x 2 maximum variance n observations / datapoints p variables Find new variable (feature) that 
 p captures most of the variance. y n x 1 . . . y 1

  3. Sparse PCA Direction of 
 x 2 maximum variance n observations / datapoints p variables Find new variable (feature) that 
 p captures most of the variance. y n x 1 . . . y 1 Empirical 
 y > cov. matrix i n X b y i y > Σ = 1 y i k x k 2 = 1 n · i i =1

  4. Sparse PCA Sparse direction of 
 maximum variance x 2 n observations / datapoints p variables Find new variable (feature) that 
 p captures most of the variance. y n x 1 . . . y 1 NP-Hard Empirical 
 y > cov. matrix i n X b y i y > Σ = 1 y i k x k 2 = 1 n · i i =1 k x k 0 = k

  5. Sparse PCA Why sparsity? [ Engineer ] Extracted feature is more interpretable ; it depends on only a few original variables. [ Statistician ] Recovery of “true” PC in high dimensions; # observations << # variables.

  6. Sparse PCA Why sparsity? More structure…? [ Engineer ] Extracted feature is more interpretable ; More interpretable . it depends on only a few original variables. [ Statistician ] Better sample complexity. Recovery of “true” PC in high dimensions; # observations << # variables. E.g. wavelets of natural images, block structures, periodical neuronal spikes, … [Baraniuk et al., 2008; Kyrillidis et al., 2014, Friedman et al., 2010, …]

  7. Sparse PCA Why sparsity? More structure…? [ Engineer ] Extracted feature is more interpretable ; More interpretable . it depends on only a few original variables. [ Statistician ] Better sample complexity. Recovery of “true” PC in high dimensions; # observations << # variables. E.g. wavelets of natural images, block structures, periodical neuronal spikes, … [Baraniuk et al., 2008; Kyrillidis et al., 2014, Friedman et al., 2010, …] • Structured sparse PCA [Jenatton et al., 2010] - Sparsity-inducing norm - 2D grid, rectangular nonzero patterns

  8. [ PCA On Graph Paths ]

  9. Problem Definition • Structure captured by an underlying graph. Directed, 
 x 1 x 1 Acyclic x 2 x 3 . p . x i T S . x 2 x i . . . x p Active variables 
 on s ⤳ t path

  10. Problem Definition • Structure captured by an underlying graph. Directed, 
 x 1 x 1 Acyclic x 2 x 3 . p . x i T S . x 2 x i . . . x p Active variables 
 on s ⤳ t path Graph Path 
 PCA

  11. Motivation 1: Neuroscience - Variables: “ voxels” (points in the brain) - Measurements: blood-oxygen levels

  12. Motivation 1: Neuroscience - Variables: “ voxels” (points in the brain) - Measurements: blood-oxygen levels T S

  13. Motivation 2: Finance - Variables: stocks - Measurements: prices over time - Goal : Find subset that explains variance

  14. Motivation 2: Finance - Variables: stocks divided in sectors - Measurements: prices over time - Goal : Find subset that explains variance 1 stock/ sector

  15. Motivation 2: Finance - Variables: stocks divided in sectors - Measurements: prices over time - Goal : Find subset that explains variance 1 stock/ sector Chase BofA UBS

  16. Motivation 2: Finance - Variables: stocks divided in sectors - Measurements: prices over time - Goal : Find subset that explains variance 1 stock/ sector BANKS Chase BofA UBS

  17. Motivation 2: Finance - Variables: stocks divided in sectors - Measurements: prices over time - Goal : Find subset that explains variance 1 stock/ sector BANKS Chase Chevron Shell BofA UBS

  18. Motivation 2: Finance - Variables: stocks divided in sectors - Measurements: prices over time - Goal : Find subset that explains variance 1 stock/ sector BANKS ENERGY Chase Chevron Shell BofA UBS

  19. Motivation 2: Finance - Variables: stocks divided in sectors - Measurements: prices over time - Goal : Find subset that explains variance 1 stock/ sector BANKS ENERGY Chase Chevron Shell BofA UBS

  20. Motivation 2: Finance - Variables: stocks divided in sectors - Measurements: prices over time - Goal : Find subset that explains variance 1 stock/ sector BANKS ENERGY Chase Chevron Shell BofA UBS

  21. Motivation 2: Finance - Variables: stocks divided in sectors - Measurements: prices over time - Goal : Find subset that explains variance 1 stock/ sector BANKS ENERGY Chase Chevron Shell BofA UBS T S

  22. Motivation 2: Finance - Variables: stocks divided in sectors - Measurements: prices over time - Goal : Find subset that explains variance 1 stock/ sector BANKS ENERGY Chase Chevron Shell BofA UBS T S

  23. [ Statistical Analysis ]

  24. Data model (p,k,d)-layer graph 2 · · · 3 = d T S p = d 1 . . . . . . . . . . . . . . . p − 2 · · · p − 2 k k layers

  25. Data model (p,k,d)-layer graph 2 · · · Target Source vertex vertex 3 = d T S p = d 1 . . . . . . . . . . . . . . . p − 2 · · · p − 2 k k layers

  26. Data model layer (p,k,d)-layer graph 2 · · · Target Source vertex vertex 3 = d T S p = d 1 . . . . . . . . . . . . . . . p − 2 · · · p − 2 k k layers

  27. Data model layer (p,k,d)-layer graph in & out degree 2 · · · Target Source vertex vertex 3 = d T S p = d 1 . . . . . . . . . . . . . . . p − 2 · · · p − 2 k k layers

  28. Data model layer (p,k,d)-layer graph in & out degree 2 · · · Target Source vertex vertex 3 = d T S p = d 1 . . . . . . . . . . . . . . . p − 2 · · · p − 2 k k layers Spike along a path Gaussian p noise (i.i.d) � · u i · x ? + z i , y i = Samples Signal, supported on path of G.

  29. Bounds [ Theorem 1 ] G (unknown) : -layer graph (known). : signal support on st-path of . ( p, k, d ) G x ? N ( 0 , β · x ? x > Observe sequence y 1 , . . . , y n of i.i.d. samples from . ? + I ) b b Σ x log p ⇣ ⌘ n = O k + k log d Then, samples suffice for recovery.

  30. Bounds [ Theorem 1 ] G (unknown) : -layer graph (known). : signal support on st-path of . ( p, k, d ) G x ? N ( 0 , β · x ? x > Observe sequence y 1 , . . . , y n of i.i.d. samples from . ? + I ) b b Σ x k log p log p ⇣ ⌘ ⇣ ⌘ vs Ω n = O k + k log d Then, samples suffice for recovery. k for sparse PCA.

  31. Bounds [ Theorem 1 ] G (unknown) : -layer graph (known). : signal support on st-path of . ( p, k, d ) G x ? N ( 0 , β · x ? x > Observe sequence y 1 , . . . , y n of i.i.d. samples from . ? + I ) b b Σ x k log p log p ⇣ ⌘ ⇣ ⌘ vs Ω n = O k + k log d Then, samples suffice for recovery. k for sparse PCA. [ Theorem 2 ] That many samples are also necessary .

  32. Bounds [ Theorem 1 ] G (unknown) : -layer graph (known). : signal support on st-path of . ( p, k, d ) G x ? N ( 0 , β · x ? x > Observe sequence y 1 , . . . , y n of i.i.d. samples from . ? + I ) NP-HARD b b Σ x k log p log p ⇣ ⌘ ⇣ ⌘ vs Ω n = O k + k log d Then, samples suffice for recovery. k for sparse PCA. [ Theorem 2 ] That many samples are also necessary .

  33. Algorithms

  34. Algorithm 1 A Power Method-based approach. Input: init x 0 , i ← 0 w i ← b Σ x i Power Iteration 
 with projection 
 step. End? b x ← x i +1

  35. [ Projection Step ] Project a p-dimensional on w x ∈ X ( G ) k x � w k 2 arg min T S

  36. [ Projection Step ] Project a p-dimensional on w x ∈ X ( G ) k x � w k 2 arg min Due to the 
 constraints. T S

  37. [ Projection Step ] Project a p-dimensional on w x ∈ X ( G ) k x � w k 2 arg min Due to the 
 constraints. T S Due to 
 Cauchy -Schwarz

  38. [ Projection Step ] Project a p-dimensional on w x ∈ X ( G ) k x � w k 2 arg min Due to the 
 constraints. T S Due to 
 Cauchy -Schwarz Longest (weighted) path 
 problem on G, with 
 G acyclic; special weights!

  39. [ Experiments ]

  40. Synthetic Data generated according to the (p,k,d)-layer graph model. (p=1000, k=50, d=10 , 100 MC iterations) 1.4 Trunc. Power M. Span. k -sparse 1.2 Graph Power M. Low-D Sampling 1 x > ! xx > k F 0.8 0.6 x b k b 0.4 0.2 0 1000 2000 3000 4000 5000 Samples n

  41. Neuroscience • Resting state fMRI dataset.* • 111 regions of interest (ROIs) (variables), extracted based on Harvard-Oxford Atlas [Desikan et al., 2006]. • Graph extracted based on Euclidean distances between center of mass of ROIs. Identified core neural components of the brain’s memory network. *[Human Connectome Project, WU-Minn Consortium]

Recommend


More recommend