Математические методы прогнозирования (практика, В.В. Стрижов)/Группа 574, осень 2019
Материал из MachineLearning.
(Различия между версиями)
(→Группа) |
(→Seminar 12 (Bakhteev, slides)) |
||
(27 промежуточных версий не показаны.) | |||
Строка 4: | Строка 4: | ||
Short link [http://bit.ly/IS_B2 bit.ly/IS_B2] | Short link [http://bit.ly/IS_B2 bit.ly/IS_B2] | ||
- | === Группа === | + | This series of seminars continues the course Bayesian model selection and investigates the theoretical aspects of model selection in various application problems. |
+ | |||
+ | Videolectures are available [https://www.youtube.com/playlist?list=PLk4h7dmY2eYH9RtoKGzxHKji0GLiBzSlZ here]. | ||
+ | |||
+ | ==== Seminar 1 (Isachenko, [[Медиа:Isachenko2019DeepGenerativeModels1.pdf|slides]]) ==== | ||
+ | * Generative models | ||
+ | * Applications | ||
+ | * Autoregressive models (CharRNN, MADE, WaveNet, PixelCNN) | ||
+ | |||
+ | ==== Seminar 2 (Isachenko, [[Медиа:Isachenko2019DeepGenerativeModels2.pdf|slides]]) ==== | ||
+ | * Generative vs discriminative | ||
+ | * Latent variable models | ||
+ | * Variational Inference | ||
+ | * ELBO | ||
+ | * Variational Autoencoder | ||
+ | |||
+ | ==== Seminar 3 (Isachenko, [[Медиа:Isachenko2019DeepGenerativeModels3.pdf|slides]]) ==== | ||
+ | * Mean field approximation | ||
+ | * Flow models (NICE, RealNVP) | ||
+ | |||
+ | ==== Seminar 4 (Isachenko, [[Медиа:Isachenko2019DeepGenerativeModels4.pdf|slides]]) ==== | ||
+ | * VAE Limitations | ||
+ | * Flows in VAE | ||
+ | * Autoregressive flows (MAF, IAF, Parallel WaveNet) | ||
+ | |||
+ | ==== Seminar 5 (Isachenko, [[Медиа:Isachenko2019DeepGenerativeModels5.pdf|slides]]) ==== | ||
+ | * IWAE (lower bound, posterior, inactive units) | ||
+ | * ELBO surgery | ||
+ | * VampPrior | ||
+ | |||
+ | ==== Seminar 6 (Isachenko, [[Медиа:Isachenko2019DeepGenerativeModels6.pdf|slides]]) ==== | ||
+ | * Autoregressive decoder in VAE | ||
+ | * Posterior collapse, decoder weakening | ||
+ | * Disentangled representations | ||
+ | * beta-VAE | ||
+ | |||
+ | ==== Seminar 7 (Bakhteev, [https://github.com/bahleg/tex_slides/raw/master/oct_19/slides1_elbo.pdf slides]) ==== | ||
+ | * Model selection statement | ||
+ | * ELBO for model selection | ||
+ | * Early Stopping is Nonparametric Variational Inference | ||
+ | * Langevin dynamics | ||
+ | |||
+ | ==== Seminar 8 (Bakhteev, [https://github.com/bahleg/tex_slides/raw/master/oct_19/slides2_hyper.pdf slides]) ==== | ||
+ | * Hyperparameter optimization | ||
+ | * Bi-level optimization | ||
+ | * RMD | ||
+ | * Gradient optimization | ||
+ | |||
+ | ==== Seminar 9 (Grabovoy, [https://github.com/andriygav/EMprior/blob/master/Lecture/Grabovoy2019EMprior.pdf slides]) ==== | ||
+ | * Mixture of Models | ||
+ | * Mixture of Experts | ||
+ | * Priors on the local Models | ||
+ | |||
+ | ==== Seminar 10 (Isachenko, [[Медиа:Isachenko2019DeepGenerativeModels7.pdf|slides]]) ==== | ||
+ | * Reversible Residual Networks | ||
+ | * Glow | ||
+ | * Neural ODE | ||
+ | |||
+ | ==== Seminar 11 (Bakhteev, [https://github.com/bahleg/tex_slides/raw/master/oct_19/slides3_meta.pdf slides]) ==== | ||
+ | * Meta-optimization | ||
+ | * Pruning | ||
+ | * Structure sampling | ||
+ | |||
+ | ==== Seminar 12 (Bakhteev, [https://github.com/bahleg/tex_slides/raw/master/oct_19/slides4_struct.pdf slides]) ==== | ||
+ | * ARD | ||
+ | * AdaNet | ||
+ | * NAS | ||
+ | * Gumbel-Softmax | ||
+ | * Variational inference with structure generation | ||
+ | |||
+ | == Группа == | ||
+ | |||
+ | === 5 курс === | ||
{|class="wikitable" | {|class="wikitable" | ||
|- | |- | ||
! Студент | ! Студент | ||
! Тест 1 | ! Тест 1 | ||
- | |||
! Тест 2 | ! Тест 2 | ||
+ | ! Тест 3 | ||
+ | ! Тест 4 | ||
+ | ! Тест 5 | ||
+ | ! HW 1 | ||
+ | ! HW 2 | ||
|- | |- | ||
|Васильев Илья | |Васильев Илья | ||
| - | | - | ||
- | | | + | | - |
- | | | + | | 0.59 |
+ | | - | ||
+ | | - | ||
+ | | - | ||
+ | | | ||
|- | |- | ||
|Гадаев Тамаз Тазикоевич | |Гадаев Тамаз Тазикоевич | ||
| 0.56 | | 0.56 | ||
- | | | + | | 0.94 |
- | | | + | | 0.75 |
+ | | - | ||
+ | | 0.88 | ||
+ | | - | ||
+ | | | ||
|- | |- | ||
|Гладин Егор Леонидович | |Гладин Егор Леонидович | ||
| - | | - | ||
- | | | + | | - |
- | | | + | | - |
+ | | - | ||
+ | | - | ||
+ | | - | ||
+ | | | ||
|- | |- | ||
|[[Участник:andriygav|Грабовой Андрей Валериевич]] | |[[Участник:andriygav|Грабовой Андрей Валериевич]] | ||
| 0.63 | | 0.63 | ||
+ | | 0.31 | ||
+ | | 0.67 | ||
+ | | 0 | ||
+ | | - | ||
|[[Media:Grabovoy2019Course5HM1.pdf|Essay]] | |[[Media:Grabovoy2019Course5HM1.pdf|Essay]] | ||
- | | | + | | |
|- | |- | ||
| Кислинский Вадим Геннадьевич | | Кислинский Вадим Геннадьевич | ||
| - | | - | ||
- | | | + | | - |
- | | | + | | - |
+ | | - | ||
+ | | - | ||
+ | | - | ||
+ | | | ||
|- | |- | ||
| Козлинский Евгений Михайлович | | Козлинский Евгений Михайлович | ||
| - | | - | ||
- | | | + | | - |
- | | | + | | - |
+ | | - | ||
+ | | - | ||
+ | | - | ||
+ | | | ||
|- | |- | ||
| Криницкий Константин Денисович | | Криницкий Константин Денисович | ||
| - | | - | ||
- | | | + | | 0.25 |
- | | | + | | - |
+ | | - | ||
+ | | - | ||
+ | |[https://drive.google.com/file/d/1xk2uvz6FmWz0s1SCleF56pRFsTlXvQ8_/view?usp=sharing essay] | ||
+ | | | ||
|- | |- | ||
| Кириллов Егор Дмитриевич | | Кириллов Егор Дмитриевич | ||
| - | | - | ||
- | | | + | | - |
- | | | + | | - |
+ | | - | ||
+ | | - | ||
+ | | - | ||
+ | | | ||
|- | |- | ||
| Рогозина Анна Андреевна | | Рогозина Анна Андреевна | ||
| - | | - | ||
- | | | + | | - |
- | | | + | | - |
+ | | - | ||
+ | | - | ||
+ | | - | ||
+ | | | ||
|- | |- | ||
| Плетнев Никита Вячеславович | | Плетнев Никита Вячеславович | ||
| 0.82 | | 0.82 | ||
- | | | + | | 0.25 |
- | [https://drive.google.com/a/phystech.edu/file/d/1kkqHZDR2ATzWtf8FRc8BjbcNAXaApvy1/view?usp=drivesdk Essay] | + | | 0.67 |
- | | | + | | - |
+ | | 0.63 | ||
+ | |[https://drive.google.com/a/phystech.edu/file/d/1kkqHZDR2ATzWtf8FRc8BjbcNAXaApvy1/view?usp=drivesdk Essay] | ||
+ | | | ||
|- | |- | ||
| Малиновский Григорий Станиславович | | Малиновский Григорий Станиславович | ||
| 0.82 | | 0.82 | ||
- | || | + | | 0.81 |
- | | | + | | 0.84 |
+ | | 1 | ||
+ | | 0.63 | ||
+ | ||[https://drive.google.com/file/d/1UkmIDJgZEDTtzSk_a20IZlTy62F2tnJB/view?usp=sharing|task_1] | ||
+ | | | ||
|- | |- | ||
| Самохина Алина Максимовна | | Самохина Алина Максимовна | ||
| - | | - | ||
- | | | + | | - |
- | | | + | | 0.25 |
+ | | 1 | ||
+ | | 0.75 | ||
+ | | - | ||
+ | | | ||
|- | |- | ||
| Султанов Азат Русланович | | Султанов Азат Русланович | ||
| - | | - | ||
- | | | + | | - |
- | | | + | | - |
+ | | - | ||
+ | | - | ||
+ | | - | ||
+ | | | ||
|- | |- | ||
| Федосов Павел Андреевич | | Федосов Павел Андреевич | ||
| - | | - | ||
- | | | + | | - |
- | | | + | | - |
+ | | - | ||
+ | | - | ||
+ | | - | ||
+ | | | ||
|- | |- | ||
| Шульгин Егор Владимирович | | Шульгин Егор Владимирович | ||
+ | | - | ||
+ | | - | ||
+ | | 0.34 | ||
+ | | - | ||
+ | | - | ||
+ | | 0.13 | ||
+ | | | ||
+ | |- | ||
+ | |} | ||
+ | |||
+ | === 6 курс === | ||
+ | {|class="wikitable" | ||
+ | |- | ||
+ | ! Студент | ||
+ | ! HW 1 | ||
+ | ! HW 2 | ||
+ | |- | ||
+ | | Сайранов Данил | ||
| - | | - | ||
| | | | ||
+ | |- | ||
+ | | Александра Гальцева | ||
+ | | - | ||
+ | | | ||
+ | |- | ||
+ | | Фельдман Даниил | ||
+ | | - | ||
| | | | ||
|- | |- | ||
| Никитин Филипп | | Никитин Филипп | ||
- | | | + | | - |
- | + | ||
| | | | ||
|- | |- | ||
| Фалахов И | | Фалахов И | ||
- | | | + | | - |
| | | | ||
+ | |- | ||
+ | | Собраков | ||
+ | | - | ||
| | | | ||
|- | |- | ||
Строка 101: | Строка 259: | ||
- | + | * Topics | |
- | + | ||
- | + | ||
- | * | + | |
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
** Generative adversarial networks | ** Generative adversarial networks | ||
- | |||
** Methods of model selection | ** Methods of model selection | ||
** Generalization theorem | ** Generalization theorem | ||
- | |||
** Complexity theorems | ** Complexity theorems | ||
- | |||
** Mixture of experts | ** Mixture of experts | ||
** Priors on the mixture | ** Priors on the mixture | ||
** Privileged learning and distilling | ** Privileged learning and distilling | ||
- | |||
** Theorem of number of experts | ** Theorem of number of experts | ||
- | |||
** Prior propagation for deep learning networks | ** Prior propagation for deep learning networks | ||
- | |||
** Directional Bayesian statistics | ** Directional Bayesian statistics | ||
- | |||
** Bayesian structure learning | ** Bayesian structure learning | ||
- | |||
** Probabilistic metric space construction | ** Probabilistic metric space construction | ||
- | |||
** Informative prior | ** Informative prior | ||
- | |||
** Bayesian programming | ** Bayesian programming | ||
- | + | ** Informative prior with applications | |
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | + | ||
- | * Informative prior with applications | + |
Текущая версия
Short link bit.ly/IS_B2
This series of seminars continues the course Bayesian model selection and investigates the theoretical aspects of model selection in various application problems.
Videolectures are available here.
Seminar 1 (Isachenko, slides)
- Generative models
- Applications
- Autoregressive models (CharRNN, MADE, WaveNet, PixelCNN)
Seminar 2 (Isachenko, slides)
- Generative vs discriminative
- Latent variable models
- Variational Inference
- ELBO
- Variational Autoencoder
Seminar 3 (Isachenko, slides)
- Mean field approximation
- Flow models (NICE, RealNVP)
Seminar 4 (Isachenko, slides)
- VAE Limitations
- Flows in VAE
- Autoregressive flows (MAF, IAF, Parallel WaveNet)
Seminar 5 (Isachenko, slides)
- IWAE (lower bound, posterior, inactive units)
- ELBO surgery
- VampPrior
Seminar 6 (Isachenko, slides)
- Autoregressive decoder in VAE
- Posterior collapse, decoder weakening
- Disentangled representations
- beta-VAE
Seminar 7 (Bakhteev, slides)
- Model selection statement
- ELBO for model selection
- Early Stopping is Nonparametric Variational Inference
- Langevin dynamics
Seminar 8 (Bakhteev, slides)
- Hyperparameter optimization
- Bi-level optimization
- RMD
- Gradient optimization
Seminar 9 (Grabovoy, slides)
- Mixture of Models
- Mixture of Experts
- Priors on the local Models
Seminar 10 (Isachenko, slides)
- Reversible Residual Networks
- Glow
- Neural ODE
Seminar 11 (Bakhteev, slides)
- Meta-optimization
- Pruning
- Structure sampling
Seminar 12 (Bakhteev, slides)
- ARD
- AdaNet
- NAS
- Gumbel-Softmax
- Variational inference with structure generation
Группа
5 курс
Студент | Тест 1 | Тест 2 | Тест 3 | Тест 4 | Тест 5 | HW 1 | HW 2 |
---|---|---|---|---|---|---|---|
Васильев Илья | - | - | 0.59 | - | - | - | |
Гадаев Тамаз Тазикоевич | 0.56 | 0.94 | 0.75 | - | 0.88 | - | |
Гладин Егор Леонидович | - | - | - | - | - | - | |
Грабовой Андрей Валериевич | 0.63 | 0.31 | 0.67 | 0 | - | Essay | |
Кислинский Вадим Геннадьевич | - | - | - | - | - | - | |
Козлинский Евгений Михайлович | - | - | - | - | - | - | |
Криницкий Константин Денисович | - | 0.25 | - | - | - | essay | |
Кириллов Егор Дмитриевич | - | - | - | - | - | - | |
Рогозина Анна Андреевна | - | - | - | - | - | - | |
Плетнев Никита Вячеславович | 0.82 | 0.25 | 0.67 | - | 0.63 | Essay | |
Малиновский Григорий Станиславович | 0.82 | 0.81 | 0.84 | 1 | 0.63 | [1] | |
Самохина Алина Максимовна | - | - | 0.25 | 1 | 0.75 | - | |
Султанов Азат Русланович | - | - | - | - | - | - | |
Федосов Павел Андреевич | - | - | - | - | - | - | |
Шульгин Егор Владимирович | - | - | 0.34 | - | - | 0.13 |
6 курс
Студент | HW 1 | HW 2 |
---|---|---|
Сайранов Данил | - | |
Александра Гальцева | - | |
Фельдман Даниил | - | |
Никитин Филипп | - | |
Фалахов И | - | |
Собраков | - |
- Topics
- Generative adversarial networks
- Methods of model selection
- Generalization theorem
- Complexity theorems
- Mixture of experts
- Priors on the mixture
- Privileged learning and distilling
- Theorem of number of experts
- Prior propagation for deep learning networks
- Directional Bayesian statistics
- Bayesian structure learning
- Probabilistic metric space construction
- Informative prior
- Bayesian programming
- Informative prior with applications