Загрузка видео...

Не удалось загрузить видео

На главную

Stein Variational Gradient Descent (SVGD) is a particle-based approach to variational inference. SVGD iteratively transports a set of particles to match a target distribution by applying a form of functional gradient descent that minimizes the KL divergence.

alec_helbling's profile picture

Alec Helbling

10,755 subscribers

28,173 просмотров • 3 месяцев назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Langevin Monte Carlo allows you to draw samples from a probability distribution using its log gradient ∇ log p(x). By performing a sort of gradient ascent with noise you can navigate around the distribution. Langevin MC is heavily related to modern diffusion models.
0:19

Langevin Monte Carlo allows you to draw samples from a probability distribution using its log gradient ∇ log p(x). By performing a sort of gradient ascent with noise you can navigate around the distribution. Langevin MC is heavily related to modern diffusion models.

Alec Helbling

96,895 просмотров • 1 год назад

Oldies but goldies: Y Nesterov, A method for solving a convex programming problem with convergence rate O(1/k^2). Improves the 1/k rate of vanilla gradient descent to 1/k^2.
0:10

Oldies but goldies: Y Nesterov, A method for solving a convex programming problem with convergence rate O(1/k^2). Improves the 1/k rate of vanilla gradient descent to 1/k^2.

Gabriel Peyré

47,883 просмотров • 1 год назад

Flow Matching aims to learn a "flow" that transforms a simple source distribution (e.g. Gaussian) to an arbitrarily complex target distribution. This video shows the evolution of the marginal probability path as a source distribution is transformed to a target distribution.
0:13

Flow Matching aims to learn a "flow" that transforms a simple source distribution (e.g. Gaussian) to an arbitrarily complex target distribution. This video shows the evolution of the marginal probability path as a source distribution is transformed to a target distribution.

Alec Helbling

150,686 просмотров • 1 год назад

Introducing "Plant gradient map"✨ This gradient set is perfect for adding a unified coloring to your forest illustrations. Use it on grayscale drawings for the best result and choose from over 30 gradients🌳 🔽Details here:
0:17

Introducing "Plant gradient map"✨ This gradient set is perfect for adding a unified coloring to your forest illustrations. Use it on grayscale drawings for the best result and choose from over 30 gradients🌳 🔽Details here:

CLIP STUDIO PAINT

20,600 просмотров • 18 дней назад

Drones followed by a wave of missiles. Tehran is applying the drone approach to disperse air defenses and facilitate hypersonic missile wave missions.
0:17

Drones followed by a wave of missiles. Tehran is applying the drone approach to disperse air defenses and facilitate hypersonic missile wave missions.

𝕊𝕡𝕣𝕚𝕟𝕥𝕖𝕣 𝕻𝕣𝕖𝕤𝕤

528,858 просмотров • 1 год назад

[VAE] by Hand ✍️ A Variational Auto Encoder (VAE) learns the structure (mean and variance) of hidden features and generates new data from the learned structure. In contrast, GANs only learn to generate new data to fool a discriminator; they may not necessarily know the underlying structure of the data. The International Conference on Learning Representations (ICLR) this year announced its first ever "Test of Time Award" to recognizes the VAE paper, published 10 years ago. This exercise demonstrates how to calculate a VAE by hand. [1] Given: ↳ Three training examples X1, X2, X3 ↳ Copy training examples to the bottom ↳ The purpose is to train the network to reconstruct the training examples. ↳ Since each target is a training example itself, we use the Greek word "auto" which means "self." This crucial step is what makes an autoencoder "auto." [2] Encoder: Layer 1 + ReLU ↳ Multiply inputs with weights and biases ↳ Apply ReLU, crossing out negative values (-1 -> 0) [3] Encoder: Mean and Variance ↳ Multiply features with two sets of weights and biases ↳ 🟩 The first set predicts the means (𝜇) of latent distributions ↳ 🟪 The second set predicts the standard deviation (𝜎) of latent distributions [4] Reparameterization Trick: Random Offset ↳ Sample epsilon ε from the normal distribution with mean = 0 and variance = 1. ↳ The purpose is to randomly pick a offset away from the mean. ↳ Multiply the standard deviation values with epsilon values. ↳ The purpose is to scale the offset by the standard deviation. [5] Reparameterization Trick: Mean + Offset ↳ Add the sampled offset to predicted mean ↳ The result are new parameters or features 🟨 as inputs to the Decoder. [6] Decoder: Layer 1 + ReLU ↳ Multiply input features with weights and biases ↳ Apply ReLU, crossing out negative values. Here, -4 is crossed out. [7] Decoder: Layer 2 ↳ Multiply features with weights and biases ↳ The output is Decoder's attempt to reconstruct the input data X from reparameterized distributions described by 𝜇 and 𝜎. [8]-[10] KL Divergence Loss [8] Loss Gradient: Mean 𝜇 ↳ We want 𝜇 to approach 0. ↳ A lot of math called SGVB simplifies the calculation of loss gradients to simply 𝜇 [9,10] Loss Gradient: Stdev 𝜎 ↳ We want 𝜎 to approach 1. ↳ A lot of math simplifies the calculation to 𝜎 - (1/ 𝜎) [11] Reconstruction Loss ↳ We want the reconstructed data Y (dark 🟧) to be the same as the input data X. ↳ Some math involving Mean Square Error simplifies the calculation to Y - X.
0:11

[VAE] by Hand ✍️ A Variational Auto Encoder (VAE) learns the structure (mean and variance) of hidden features and generates new data from the learned structure. In contrast, GANs only learn to generate new data to fool a discriminator; they may not necessarily know the underlying structure of the data. The International Conference on Learning Representations (ICLR) this year announced its first ever "Test of Time Award" to recognizes the VAE paper, published 10 years ago. This exercise demonstrates how to calculate a VAE by hand. [1] Given: ↳ Three training examples X1, X2, X3 ↳ Copy training examples to the bottom ↳ The purpose is to train the network to reconstruct the training examples. ↳ Since each target is a training example itself, we use the Greek word "auto" which means "self." This crucial step is what makes an autoencoder "auto." [2] Encoder: Layer 1 + ReLU ↳ Multiply inputs with weights and biases ↳ Apply ReLU, crossing out negative values (-1 -> 0) [3] Encoder: Mean and Variance ↳ Multiply features with two sets of weights and biases ↳ 🟩 The first set predicts the means (𝜇) of latent distributions ↳ 🟪 The second set predicts the standard deviation (𝜎) of latent distributions [4] Reparameterization Trick: Random Offset ↳ Sample epsilon ε from the normal distribution with mean = 0 and variance = 1. ↳ The purpose is to randomly pick a offset away from the mean. ↳ Multiply the standard deviation values with epsilon values. ↳ The purpose is to scale the offset by the standard deviation. [5] Reparameterization Trick: Mean + Offset ↳ Add the sampled offset to predicted mean ↳ The result are new parameters or features 🟨 as inputs to the Decoder. [6] Decoder: Layer 1 + ReLU ↳ Multiply input features with weights and biases ↳ Apply ReLU, crossing out negative values. Here, -4 is crossed out. [7] Decoder: Layer 2 ↳ Multiply features with weights and biases ↳ The output is Decoder's attempt to reconstruct the input data X from reparameterized distributions described by 𝜇 and 𝜎. [8]-[10] KL Divergence Loss [8] Loss Gradient: Mean 𝜇 ↳ We want 𝜇 to approach 0. ↳ A lot of math called SGVB simplifies the calculation of loss gradients to simply 𝜇 [9,10] Loss Gradient: Stdev 𝜎 ↳ We want 𝜎 to approach 1. ↳ A lot of math simplifies the calculation to 𝜎 - (1/ 𝜎) [11] Reconstruction Loss ↳ We want the reconstructed data Y (dark 🟧) to be the same as the input data X. ↳ Some math involving Mean Square Error simplifies the calculation to Y - X.

Tom Yeh

48,475 просмотров • 2 лет назад

In 2023, neuroscientists uncovered that our brain distinguishes reality from imagination on a gradient, with a threshold marking the jump from one state to another. Learn about the biological breakthroughs of 2023:
0:11

In 2023, neuroscientists uncovered that our brain distinguishes reality from imagination on a gradient, with a threshold marking the jump from one state to another. Learn about the biological breakthroughs of 2023:

Quanta Magazine

74,292 просмотров • 2 лет назад

I took album cover of GNX by Kendrick Lamar and turned it into a 3D particle model in Threejs with TSL Used Grok 4 by xAI to improve the noise that moves particles.
0:16

I took album cover of GNX by Kendrick Lamar and turned it into a 3D particle model in Threejs with TSL Used Grok 4 by xAI to improve the noise that moves particles.

Dominik Fojcik

189,972 просмотров • 1 год назад

Have you ever experienced such a high rate of descent? If something is meant to happen, it will happen—Murphy's Law.
0:12

Have you ever experienced such a high rate of descent? If something is meant to happen, it will happen—Murphy's Law.

Turbine Traveller

753,818 просмотров • 1 год назад

Introducing Better Gradient, a collaboration between Plugin Play and Ravie "The Gradient Guys" .co Now available at - Save gradient presets - Customize your color interpolation with graph easing - Significantly improved color rendering to get rid of the gross grays AE typically produces between color stops. - Animate gradients along paths with shadows - and so much more! Effortlessly blend colors into mesmerizing kaleidoscopes of gradient joy. Mapping, paths, you name it, you can gradient it. Launch video direction, design, and animation from Sam Essanoussi and Justin De Leon.
0:20

Introducing Better Gradient, a collaboration between Plugin Play and Ravie "The Gradient Guys" .co Now available at - Save gradient presets - Customize your color interpolation with graph easing - Significantly improved color rendering to get rid of the gross grays AE typically produces between color stops. - Animate gradients along paths with shadows - and so much more! Effortlessly blend colors into mesmerizing kaleidoscopes of gradient joy. Mapping, paths, you name it, you can gradient it. Launch video direction, design, and animation from Sam Essanoussi and Justin De Leon.

Austin Bauwens

18,305 просмотров • 15 дней назад

Rayen Bahri built a Blender addon around gradient (palette) texturing, making it easier to set up and use this workflow directly inside Blender. 🎨 See the details and background of the tool: #b3d #3dart
0:10

Rayen Bahri built a Blender addon around gradient (palette) texturing, making it easier to set up and use this workflow directly inside Blender. 🎨 See the details and background of the tool: #b3d #3dart

Jettelly Inc.

64,122 просмотров • 4 месяцев назад

An up-close view of TriangleSplatting+. Still hard to believe that there's a gradient leading to this dataset and that ADAM on GPUs is able to find it. Unthinkable just 5 years ago. Thanks Andrea Tagliasacchi 🇨🇦 for putting the PLY on the project page.
0:16

An up-close view of TriangleSplatting+. Still hard to believe that there's a gradient leading to this dataset and that ADAM on GPUs is able to find it. Unthinkable just 5 years ago. Thanks Andrea Tagliasacchi 🇨🇦 for putting the PLY on the project page.

Rafael Spring

26,037 просмотров • 11 месяцев назад

Saw a couple of character trail effects recently, so wanted to try something using #Niagara mesh particles. Particle uploads bone transforms used by material for skinning vertices. #UE5
0:16

Saw a couple of character trail effects recently, so wanted to try something using #Niagara mesh particles. Particle uploads bone transforms used by material for skinning vertices. #UE5

Amit Mehar

33,697 просмотров • 2 лет назад

The Gaussian Wave Packet ✍️ It is a way to describe a quantum particle, like an electron, that is located in a certain area of space instead of being spread out everywhere. It forms a bell-shaped curve, where the peak of the curve indicates the most likely place to find the particle. This shape is special because it offers the best way to pack a particle; it meets the physical limit set by the Heisenberg Uncertainty Principle, striking the best balance between knowing a particle's position and its momentum. However, because this packet consists of many different overlapping waves, it is naturally unstable for a free particle. Over time, these internal waves travel at slightly different speeds, which causes the bell curve to gradually flatten and widen. This process is known as dispersion. In simpler terms, the longer a quantum particle travels freely, the more unclear its exact location becomes. Video : Jeedecode
0:16

The Gaussian Wave Packet ✍️ It is a way to describe a quantum particle, like an electron, that is located in a certain area of space instead of being spread out everywhere. It forms a bell-shaped curve, where the peak of the curve indicates the most likely place to find the particle. This shape is special because it offers the best way to pack a particle; it meets the physical limit set by the Heisenberg Uncertainty Principle, striking the best balance between knowing a particle's position and its momentum. However, because this packet consists of many different overlapping waves, it is naturally unstable for a free particle. Over time, these internal waves travel at slightly different speeds, which causes the bell curve to gradually flatten and widen. This process is known as dispersion. In simpler terms, the longer a quantum particle travels freely, the more unclear its exact location becomes. Video : Jeedecode

ScieVision

23,147 просмотров • 6 месяцев назад

Zephyren makes a thunderous descent to Sonaria as the newest disaster event creature dropping this Friday! What do you think of Zephyren? 🌪️ #CreaturesofSonaria #RobloxDev
0:18

Zephyren makes a thunderous descent to Sonaria as the newest disaster event creature dropping this Friday! What do you think of Zephyren? 🌪️ #CreaturesofSonaria #RobloxDev

Creatures of Sonaria

13,594 просмотров • 3 месяцев назад

I'm trying to figure out where to place a joystick's digital tween when you hold a real one. The current approach is to recreate a plane based on the positions of your intermediate and proximal joints.
0:18

I'm trying to figure out where to place a joystick's digital tween when you hold a real one. The current approach is to recreate a plane based on the positions of your intermediate and proximal joints.

Oleg Frolov

21,764 просмотров • 1 год назад

This is absolutely genius. Nigel McGuinness *technically* applying a hold while Josh Woods is on the ropes, thus forcing Woods to use one of his rope breaks in a Pure Rules match. Exhibit Z of McGuinness being a wrestling savant.
0:16

This is absolutely genius. Nigel McGuinness *technically* applying a hold while Josh Woods is on the ropes, thus forcing Woods to use one of his rope breaks in a Pure Rules match. Exhibit Z of McGuinness being a wrestling savant.

Brayan

237,716 просмотров • 3 месяцев назад