Kernel Methods, part 1 - Arthur Gretton - MLSS 2020, Tübingen
Table of Contents (powered by https://videoken.com)
0:00:00 Introduction
0:02:10 Representing and comparing probabilities with kernels: Part 1
0:02:56 A motivation: comparing two samples
0:03:34 A real-life example: two-sample tests
0:04:34 Training generative models
0:06:04 A second task: testing goodness of fit
0:07:18 A third task: testing independence
0:08:37 Outline: these slides
0:10:16 Outline: next slides
0:10:43 Reproducing Kernel Hilbert Spaces
0:10:48 Kernels and feature space (1): XOR example
0:12:30 Kernels and feature space (2): smoothing
0:13:43 Hilbert space
0:17:06 New kernels from old: sums, transformations
0:18:03 New kernels from old: products
0:22:19 Sums and products =polynomials
0:22:40 Infinite sequences
0:23:21 The reproducing property
0:24:42 Infinite sequences (proof)
0:25:15 A famous infinite feature space kernel
0:27:38 Positive definite functions
0:29:43 Kernels are positive definite
0:31:48 Sum of kernels is a kernel
0:32:34 Functions of infinitely many features
0:33:22 Functions of finitely many features
0:35:07 Functions of infinitely many features
0:35:55 Expressing the functions with kernels
0:38:42 The feature map (x) is also a function
0:41:00 The reproducing property
0:41:45 Understanding smoothness in the RKHS
0:42:30 Constructing an infinite feature space: fourier series
0:47:27 Fourier series for top hat function
0:49:37 Fourier series for kernel function
0:51:49 Fourier series for Gaussian-spectrum kernel
0:53:00 RKHS via fourier series
0:59:23 Roughness penalty explained
1:03:38 Feature map and reproducing property
1:07:29 Q&A
1:09:28 Link back to original RKHS function definition
1:12:31 Main message
1:14:33 Q&A
Видео Kernel Methods, part 1 - Arthur Gretton - MLSS 2020, Tübingen канала virtual mlss2020
0:00:00 Introduction
0:02:10 Representing and comparing probabilities with kernels: Part 1
0:02:56 A motivation: comparing two samples
0:03:34 A real-life example: two-sample tests
0:04:34 Training generative models
0:06:04 A second task: testing goodness of fit
0:07:18 A third task: testing independence
0:08:37 Outline: these slides
0:10:16 Outline: next slides
0:10:43 Reproducing Kernel Hilbert Spaces
0:10:48 Kernels and feature space (1): XOR example
0:12:30 Kernels and feature space (2): smoothing
0:13:43 Hilbert space
0:17:06 New kernels from old: sums, transformations
0:18:03 New kernels from old: products
0:22:19 Sums and products =polynomials
0:22:40 Infinite sequences
0:23:21 The reproducing property
0:24:42 Infinite sequences (proof)
0:25:15 A famous infinite feature space kernel
0:27:38 Positive definite functions
0:29:43 Kernels are positive definite
0:31:48 Sum of kernels is a kernel
0:32:34 Functions of infinitely many features
0:33:22 Functions of finitely many features
0:35:07 Functions of infinitely many features
0:35:55 Expressing the functions with kernels
0:38:42 The feature map (x) is also a function
0:41:00 The reproducing property
0:41:45 Understanding smoothness in the RKHS
0:42:30 Constructing an infinite feature space: fourier series
0:47:27 Fourier series for top hat function
0:49:37 Fourier series for kernel function
0:51:49 Fourier series for Gaussian-spectrum kernel
0:53:00 RKHS via fourier series
0:59:23 Roughness penalty explained
1:03:38 Feature map and reproducing property
1:07:29 Q&A
1:09:28 Link back to original RKHS function definition
1:12:31 Main message
1:14:33 Q&A
Видео Kernel Methods, part 1 - Arthur Gretton - MLSS 2020, Tübingen канала virtual mlss2020
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
![Kernel Methods, part 2 - Arthur Gretton - MLSS 2020, Tübingen](https://i.ytimg.com/vi/eANiXrWO1dM/default.jpg)
![MLSS2020 Talent Show](https://i.ytimg.com/vi/XNTw7pUKcdY/default.jpg)
![Inner Products in Hilbert Space](https://i.ytimg.com/vi/g-eNeXlZKAQ/default.jpg)
![Vlog 06 Yoshua & Yee Whye](https://i.ytimg.com/vi/zDedjNnTBw4/default.jpg)
![Interpretable Comparison of Distributions and Models | NeurIPS 2019](https://i.ytimg.com/vi/DuCmMyz7fkc/default.jpg)
![Warp Drive and Aliens: Bryan Gaensler Public Lecture](https://i.ytimg.com/vi/fzweIEvN8sc/default.jpg)
![Geometric Deep Learning - Michael Bronstein - MLSS 2020, Tübingen](https://i.ytimg.com/vi/8kTxTX0eBRA/default.jpg)
![Jiun Shyan Chen, "A new reproducing Kernel formulation with embedded Kernel stability..."](https://i.ytimg.com/vi/FncBGiebqWk/default.jpg)
![But what is a neural network? | Chapter 1, Deep learning](https://i.ytimg.com/vi/aircAruvnKk/default.jpg)
![Kernels - Bernhard Schölkopf - MLSS 2013 Tübingen](https://i.ytimg.com/vi/uzWgB1VO9xQ/default.jpg)
![Machine Learning: Support Vector Machine - Kernel Trick](https://i.ytimg.com/vi/vMmG_7JcfIc/default.jpg)
![Vlog 08 Mihaela & Arthur](https://i.ytimg.com/vi/vLPkdL3h-MA/default.jpg)
![Brian Cox Lecture - GCSE Science brought down to Earth](https://i.ytimg.com/vi/enSXh4YY9Ws/default.jpg)
![The Kernel Trick](https://i.ytimg.com/vi/N_r9oJxSuRs/default.jpg)
![Arthur Gretton Kernel methods for comparing distributions and training generative models](https://i.ytimg.com/vi/5sijxSg8P14/default.jpg)
![Banned TED Talk: The Science Delusion - Rupert Sheldrake at TEDx Whitechapel](https://i.ytimg.com/vi/1TerTgDEgUE/default.jpg)
![The Kernel Trick - THE MATH YOU SHOULD KNOW!](https://i.ytimg.com/vi/wBVSbVktLIY/default.jpg)
![Bayesian Inference, part 1 - Shakir Mohamed - MLSS 2020, Tübingen](https://i.ytimg.com/vi/x4Y90zPjbq0/default.jpg)
![Intro to Kernel Density Estimation](https://i.ytimg.com/vi/x5zLaWT5KPs/default.jpg)
![Time Series Talk : Stationarity](https://i.ytimg.com/vi/oY-j2Wof51c/default.jpg)