jubilee of fourier analysis and applications in
play

Jubilee of Fourier Analysis and Applications In Celebration of John - PowerPoint PPT Presentation

The Cumulative Distribution Transform For Data Analysis And Machine Learning Akram Aldroubi Vanderbilt University Jubilee of Fourier Analysis and Applications In Celebration of John Benedetto 80th Birthday Typeset by Foil T EX Jubilee-


  1. The Cumulative Distribution Transform For Data Analysis And Machine Learning Akram Aldroubi Vanderbilt University Jubilee of Fourier Analysis and Applications In Celebration of John Benedetto 80th Birthday – Typeset by Foil T EX –

  2. Jubilee- 2019 Supported by NIH Grant (Gustavo Rohde PI) Gustavo Rohde – Typeset by Foil T EX – Akram Aldroubi

  3. Jubilee- 2019 Transports Transform Transforms: Fourier Transform, Wavelet transform, Zak Transform, Shearlets, Scattering “transform,”... – Typeset by Foil T EX – Akram Aldroubi

  4. Jubilee- 2019 Transports Transform Transforms: Fourier Transform, Wavelet transform, Zak Transform, Shearlets, Scattering “transform,”... Transport Transforms: Non-linear transforms based on transport theory: Monge and Katorovich Transport theory – Typeset by Foil T EX – Akram Aldroubi

  5. Jubilee- 2019 The Monge Problem (1781) The Monge Problem Let µ be a pile of sand on X ⊂ R n , find the ”most efficient way” to transport it to the hole in the ground ν on X ⊂ R n . – Typeset by Foil T EX – Akram Aldroubi

  6. Jubilee- 2019 The Monge Problem (1781) The Monge Problem Let µ be a pile of sand on X ⊂ R n , find the ”most efficient way” to transport it to the hole in the ground ν on X ⊂ R n . Let µ, ν be probability measures on R n find a map T † : R n → R n such � T † = arg min R n � x − T ( x ) � 2 dµ ( x ) , ν = T # µ where ν ( B ) = µ ( T − 1 ( B )) for all measurable measurable sets B . – Typeset by Foil T EX – Akram Aldroubi

  7. Jubilee- 2019 The Monge Problem (1781) The Monge Problem Let µ be a pile of sand on X ⊂ R n , find the ”most efficient way” to transport it to the hole in the ground ν on X ⊂ R n . Let µ, ν be probability measures on R n find a map T † : R n → R n such � T † = arg min R n � x − T ( x ) � 2 dµ ( x ) , ν = T # µ where ν ( B ) = µ ( T − 1 ( B )) for all measurable measurable sets B . Weak version of the Monge problem: The Kantorovich problem (1939). – Typeset by Foil T EX – Akram Aldroubi

  8. Jubilee- 2019 Brenier’s Theorem (1991) (Brenier’s Theorem) Let µ, ν be two probability measures on R n (finite 2nd moments) that are absolutely continuous w.r.t Lebesgue measure. Then there exists a map T † : R n → R n such that � T † = arg min R n � x − T ( x ) � 2 dµ ( x ) , ν = T # µ where ν ( B ) = µ ( T − 1 ( B )) for all measurable measurable sets Moreover, T † is unique. B . (Generalization by Gangbo and McCann 1996, Villani 2006) – Typeset by Foil T EX – Akram Aldroubi

  9. Jubilee- 2019 Brenier’s Theorem (1991) (Brenier’s Theorem) Let µ, ν be two probability measures on R n (finite 2nd moments) that are absolutely continuous w.r.t Lebesgue measure. Then there exists a map T † : R n → R n such that � T † = arg min R n � x − T ( x ) � 2 dµ ( x ) , ν = T # µ where ν ( B ) = µ ( T − 1 ( B )) for all measurable measurable sets Moreover, T † is unique. B . (Generalization by Gangbo and McCann 1996, Villani 2006) The transport transform: Let dµ ( x ) = s ( x ) dx and dν ( x ) = s 0 ( x ) dx , where r is a fixed reference signal, then the transform s of s is the unique solution to the Monge problem above, i.e., ˜ s = T † . ˜ – Typeset by Foil T EX – Akram Aldroubi

  10. Jubilee- 2019 The CDT transform Let s a smooth probability density function on [0 , 1] ⊂ R , and s 0 a reference probability density function on [0 , 1] ⊂ R . The Cumulative Distribution Transform ˜ s ( x ) x � � s ( ξ ) dξ = s 0 ( ξ ) dξ, x ∈ [0 , 1] . 0 0 – Typeset by Foil T EX – Akram Aldroubi

  11. Jubilee- 2019 The CDT transform Let s a smooth probability density function on [0 , 1] ⊂ R , and s 0 a reference probability density function on [0 , 1] ⊂ R . The Cumulative Distribution Transform ˜ s ( x ) x � � s ( ξ ) dξ = s 0 ( ξ ) dξ, x ∈ [0 , 1] . 0 0 Typically s 0 = χ [0 , 1] . – Typeset by Foil T EX – Akram Aldroubi

  12. Jubilee- 2019 The CDT transform Let s a smooth probability density function on [0 , 1] ⊂ R , and s 0 a reference probability density function on [0 , 1] ⊂ R . The Cumulative Distribution Transform ˜ s ( x ) x � � s ( ξ ) dξ = s 0 ( ξ ) dξ, x ∈ [0 , 1] . 0 0 Typically s 0 = χ [0 , 1] . Inverse Transform: s ′ ( x ) s (˜ ˜ s ( x )) = s 0 ( x ) . – Typeset by Foil T EX – Akram Aldroubi

  13. Jubilee- 2019 CDT and its inverse – Typeset by Foil T EX – Akram Aldroubi

  14. Jubilee- 2019 Radon-CDT – Typeset by Foil T EX – Akram Aldroubi

  15. Jubilee- 2019 Convexification properties T s : R → L 2 ( R ) : T s ( µ )( x ) = s µ ( x ) = s ( x − µ ) . – Typeset by Foil T EX – Akram Aldroubi

  16. Jubilee- 2019 Convexification properties – Typeset by Foil T EX – Akram Aldroubi

  17. Jubilee- 2019 Convexification properties – Typeset by Foil T EX – Akram Aldroubi

  18. Jubilee- 2019 Wasserstein distance between two measures Let Π( µ, ν ) be the set of all probability measures on R n × R n with marginals µ and ν . 2-Wasserstein distance between µ and ν : � W 2 R n � x − y � 2 dπ ( x, y ) . 2 ( µ, ν ) = min π ∈ Π – Typeset by Foil T EX – Akram Aldroubi

  19. Jubilee- 2019 Wasserstein distance between two measures Let Π( µ, ν ) be the set of all probability measures on R n × R n with marginals µ and ν . 2-Wasserstein distance between µ and ν : � W 2 R n � x − y � 2 dπ ( x, y ) . 2 ( µ, ν ) = min π ∈ Π Existence of a minimizer is due to Kantorovich. – Typeset by Foil T EX – Akram Aldroubi

  20. Jubilee- 2019 Wasserstein distance between two measures Let Π( µ, ν ) be the set of all probability measures on R n × R n with marginals µ and ν . 2-Wasserstein distance between µ and ν : � W 2 R n � x − y � 2 dπ ( x, y ) . 2 ( µ, ν ) = min π ∈ Π Existence of a minimizer is due to Kantorovich. The solution T † of the transport map of the Monge problem give rise to the minimizer to the Kantorovich problem: d ( µ ( x ) δ ( y = T † ( x )) ∈ Π and minimizes W 2 ( µ, ν ) . – Typeset by Foil T EX – Akram Aldroubi

  21. Jubilee- 2019 Wasserstein distance between two measures Theorem (Kolouri, Rohde ) Let s 1 and s 2 be two signals (PDFs) and ˜ s 1 , ˜ s 2 be their CDT transform with respect to fixed reference s 0 . Then � s 1 � 2 R n � x − y � 2 dπ ( x, y ) � ˜ s 2 − ˜ L 2 ( R n ) = W 2 ( µ, ν ) = min π ∈ Π where dµ ( x ) = s 1 ( x ) dx and dν = s 2 ( x ) dx . – Typeset by Foil T EX – Akram Aldroubi

  22. Jubilee- 2019 – Typeset by Foil T EX – Akram Aldroubi

  23. Jubilee- 2019 Applications – Typeset by Foil T EX – Akram Aldroubi

  24. Jubilee- 2019 Applications – Typeset by Foil T EX – Akram Aldroubi

  25. Jubilee- 2019 Applications – Typeset by Foil T EX – Akram Aldroubi

  26. Jubilee- 2019 – Typeset by Foil T EX – Akram Aldroubi

  27. Jubilee- 2019 – Typeset by Foil T EX – Akram Aldroubi

  28. Jubilee- 2019 Happy Birthday Caro – Typeset by Foil T EX – Akram Aldroubi

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend


More recommend