Questions tagged [probability-distribution]
For questions related to AI theory that relies on the knowledge of a distribution of probabilities across one or more dimensions affecting probability. Such a distribution may be in discrete buckets, such as quartile, octile, or percentile conventions or continuous functions based on some closed form (algebraic formula). Distributions of probability are key in planning, natural language handling, and other AI objectives.
78
questions
3
votes
0
answers
63
views
Relation between SDE diffusion and DDPM/DDIM
Background & Definitions
In DDPM, the diffusion backward step is described as follows (where $z\sim \mathcal{N}(0,I)$ and $x_{T}\sim \mathcal{N}(0,I)$):
and in DDIM we have
while in the SDE ...
- 79
0
votes
0
answers
8
views
Filter distribution of Latent variable models
In this paper https://arxiv.org/pdf/1907.00953.pdf, about stochastic latent variable models, the paper says "We use the
reparameterization trick to sample from the filtering distribution". I ...
- 15
3
votes
1
answer
65
views
How can I make an MNIST digit recognizer that rejects out-of-distribution data?
I've done an MNIST digit recognition neural network.
When you put images in that are completely unlike its training data, it still tries to classify them as digits. Sometimes it strongly classifies ...
- 133
1
vote
0
answers
23
views
How does the skin color follow Gaussian distribution in YCBCR?
I am still new to image processing and machine intelligence. I wanted to make a Python program that can isolate an image of a hand from the background to detect a specific hand gesture, so I came to ...
- 111
0
votes
0
answers
4
views
Bounding the True Error of a Rule on a Random Sample using Chernoff Bounds
I am currently studying machine learning PAC, and I didn't fully grasp the concept I came across this question that caught my eye and I can't handle it because I don't fully understand whats it means. ...
- 101
0
votes
0
answers
14
views
How many opposing users should be recorded exterior to the average data before being combined?
Outside of the programming toward AI, I am having difficulty putting together a plan on how this machine I hope to build would work.
The basic question is: How should it handle user reviews / ...
- 101
0
votes
0
answers
35
views
Do Neural Networks tend to have Zero Mean Errors in each Output?
My NN (a few linear layers with ReLUs + batch normalization, no activation in the last layer) learns to approximate vector-valued labels $y_z$ from data $z\sim\rho_z$ in a supervised way, i.e. net$(z)=...
- 101
0
votes
0
answers
66
views
Calculating Curiosity with Friston's Free Energy in Reinforcement Learning
I'm trying to implement the paper A Curiosity Algorithm for Robots Based on the Free Energy Principle in a reinforcement learning environment using PyTorch, but I am unclear how curiosity is ...
1
vote
1
answer
70
views
How is the variance for a diffusion kernel derived for a diffusion model?
So I'm watching this video tutorial from CVPR this year on diffusion models, and I am confused by the variance term in the distribution on the left on the video. I understand that in the forward ...
- 11
1
vote
0
answers
67
views
Why does importance sampling work with latent variable models?
Caveat: importance sampling doesn't actually work for variational auto-encoders, but the question makes sense regardless
In "L4 Latent Variable Models (VAE) -- CS294-158-SP20 Deep Unsupervised ...
- 151
0
votes
1
answer
67
views
What should be taken as random variables in the distributions of datasets?
Consider the following two paragraphs taken from the paper titles Generative Adversarial Nets by Ian J. Goodfellow et.al
#1: Abstract
We propose a new framework for estimating generative models via ...
- 3,581
0
votes
1
answer
181
views
What is the distribution of autoencoder embeddings?
Is there any result on the distribution of autoencoder embeddings?
For example, the following image (taken from this article) visualizes the latent space with t-SNE. As you can see, images from the ...
- 271
0
votes
1
answer
47
views
What is the meaning of $p_{\text {data }}(y)$ in the CycleGAN?
In the original CycleGAN paper, on the second page, there is a sentence that I didn't quite understand
In theory, this objective can induce an output distribution over $\hat{y}$ that matches the ...
- 19
1
vote
1
answer
751
views
PPO: policy loss becomes nan [closed]
I'm implement PPO for a very specific problem, and it seems to be working somewhat, but after a few epochs, I always get something like this:
...
0
votes
0
answers
152
views
Neural network for an output in the form of a probability distribution
I am not an expert in machine learning. Recently, I want to construct a data-driven model based the neural network. The problem is that I want from my algorithm to learn an output in the form of a ...
0
votes
1
answer
322
views
Are there any scale invariant activation functions that outputs probability distribution?
Softmax activation function is used to convert any random vector into a probability distribution. So, it is generally used as an activation function in the last layer of deep neural networks that are ...
- 3,581
0
votes
1
answer
58
views
Why are Directed Graphical Models considered ML methods?
Consider the following problem. The probability of being born in countries [1,2,3,4] is given by [a, b, c, d] respectively. This is a categorical problem.
Now, assume that the height of a person ...
1
vote
0
answers
13
views
How does the distribution of the parameters change in logistic regression?
I have my own data to train a logistic regression model (for a multi-class classification task), and I want to know how the distribution of weight parameters changes after each update with gradient ...
- 173
2
votes
3
answers
182
views
Are the authors of the VAE paper writing the PDFs as a function of the random variables?
Usually, I see the conventions:
discrete random variable is denoted as $X$,
the pmf is written as $P(X=x)$ or $p(X=x)$ or $p_{X}(x)$ or $p(x)$, where $x$ is an instance of $X$
a continuous random ...
- 213
1
vote
1
answer
118
views
What is the analytical formula for "Kaiming He" probability density function?
A probability density function is a real-valued function that roughly gives the density of probability at a particular value of a random variable.
For example, the probability density function of a ...
- 3,581
2
votes
1
answer
768
views
How does the VAE learn a joint distribution?
I found the following paragraph from An Introduction to
Variational Autoencoders sounds relevant, but I am not fully understanding it.
A VAE learns stochastic mappings between an observed $\mathbf{x}$...
- 213
0
votes
2
answers
85
views
Is knowing underlying probability distribution mandatory for deciding iid property of random variables?
Consider the following information regarding iid random variables
The acronym IID stands for "Independent and Identically Distributed".
A sequence of random variables (or random vectors) is ...
- 3,581
2
votes
1
answer
120
views
Which of the following probability distribution is generating an iid dataset?
Let $X_1, X_2$ be two discrete random variables. Each random variable takes two values: $1, 2$
The probability distribution $p_1$ over $X_1, X_2$ is given by
$$p_1(X_1=1, X_2 = 1) = \dfrac{1}{4}$$
$$...
- 3,581
1
vote
2
answers
318
views
How can we "draw i.i.d" from any probability distribution?
Consider the following paragraph from 2 Learning in High Dimensions in from of the paper titled Geometric Deep Learning Grids, Groups, Graphs, Geodesics, and Gauges
...
- 3,581
0
votes
1
answer
87
views
How to calculate policy probability ratio in multiple action space
I try to solve a navigation problem with PPO; my actions space have three-part:
robot linear velocity that is in [-3,3] range (getting from a tanh activation func)
robot linear angular that is in [-...
- 3
0
votes
2
answers
341
views
Where can I read about the multinoulli distribution?
I encountered the term multinoulli distribution in the following sentence from Chapter 4: Numerical Computation of the deep learning book.
The softmax function is often used to predict the ...
- 3,581
1
vote
0
answers
39
views
Are there any other metrics available for calculating the distance between two probability distributions other than those mentioned?
The divergence between two probability distributions is used in calculating the difference between the true distribution and generated distribution. These divergence metrics are used in loss functions....
- 3,581
1
vote
1
answer
290
views
Is it abuse of notation to use tilde operator in this context?
The following is a way to use tilde (∼) in context of random variables or random vectors.
In statistics, the tilde is frequently used to mean "has the
distribution (of)," for instance, $X∼N(...
- 3,581
1
vote
0
answers
223
views
Which probability distribution a generator in Generative Adversarial Network (GAN) is capturing: dataset or ground truth?
Consider the following statement from the abstract of the paper titled Generative Adversarial Nets
We propose a new framework for estimating generative models via an
adversarial process, in which we ...
- 3,581
1
vote
1
answer
936
views
How to define a continuous action distribution with a specific range for Reinforcement Learning?
Specifically for continuous control PPO, let's say my action space range is between $X$ (low) and $Y$ (high) and they are all sampled from a Gaussian Action Distribution with mean $\mu$ and standard ...
- 223
1
vote
0
answers
22
views
Rotationally independent distributions
Maxwell's theorem states that multivariate normal distribution $\mathcal{N}(\mathbf{0}, \sigma^2\mathbf{I})$ is the only distribution of a random vector that is invariant and have independent ...
- 31
0
votes
0
answers
219
views
Predicting the probability of a periodically happening event occurring at a given time
I have encountered this problem on how to predict the probability of a periodically happening event occurring at a given time.
For example, we have an event called being_an_undergrad. There are many ...
- 1
4
votes
1
answer
217
views
Why do we sample vectors from a standard normal distribution for the generator?
I am new to GANs. I noticed that everybody generates a random vector (usually 100 dimensional) from a standard normal distribution $N(0, 1)$. My question is: why? Why don't they sample these vectors ...
- 862
1
vote
1
answer
328
views
Why are CNN binary classifier output probability distributions often skewed?
I've been working on a lot of simple resnet18 binary classifiers lately and I've started to notice that the probability distributions are often skewed one way or the other. This figure shows one such ...
- 1,319
3
votes
1
answer
305
views
How can a probability density value be used for the likelihood calculation?
Consider our parametric model $p_\theta$ for an underlying probabilistic distribution $p_{data}$.
Now, the likelihood of an observation $x$ is generally defined as $L(\theta|x) = p_{\theta}(x)$.
The ...
- 3,581
2
votes
1
answer
94
views
What is emperical distribution in MLE?
I was reading the book Deep Learning by Ian Goodfellow. I had a doubt in the Maximum likelihood estimation section (Pg 131). I understand till the Eq 5.58 which describes what is being maximized in ...
7
votes
2
answers
2k
views
Why is KL divergence used so often in Machine Learning?
The KL Divergence is quite easy to compute in closed form for simple distributions -such as Gaussians- but has some not-very-nice properties. For example, it is not symmetrical (thus it is not a ...
- 233
3
votes
1
answer
88
views
Is this referring to the true underlying distribution, or the distribution of our sample?
I am currently studying the paper Learning and Evaluating Classifiers under Sample Selection Bias by Bianca Zadrozny. In the introduction, the author says the following:
One of the most common ...
- 527
3
votes
2
answers
1k
views
When should one prefer using Total Variational Divergence over KL divergence in RL
In RL, both the KL divergence (DKL) and Total variational divergence (DTV) are used to measure the distance between two policies. I'm most familiar with using DKL as an early stopping metric during ...
- 531
1
vote
0
answers
54
views
Estimating $\sigma_i$ according to maximum likelihood method
Let be a Bayesian multivariate normal distribution classifier with distinct covariance matrices for each class and isotropic, i.e. with equal values over the entire diagonal and zero otherwise, $\...
- 113
0
votes
1
answer
346
views
How to calculate v min and v max for C51 DQN
Background: In C51 DQNs you must specify a v-min/max to be used during training. The way this is generally done is you take the max score possible for the game and set that to v-max, then v-min is ...
- 153
1
vote
1
answer
420
views
In continuous action spaces, how is the standard deviation, associated with Gaussian distribution from which actions are sampled, represented?
I have a question about implementing policy gradient methods for problems with continuous action spaces.
Assume that actions are sampled from a diagonal Gaussian distribution with mean vector $\mu$ ...
- 11
1
vote
1
answer
58
views
Intuitively, why can the training of a neural network be formulated as a probability estimation problem?
Neural network training problems are oftentimes formulated as probability estimation problems (such as autoregressive models).
How does one intuitively understand this idea?
- 33
2
votes
0
answers
165
views
Is the generator distribution in GAN's continuous or discrete?
I have some trouble with the probability densities described in the original paper. My question is based on Goodfellow's paper and tutorial, respectively: Generative Adversarial Networks and NIPS ...
- 21
3
votes
1
answer
100
views
How does $\mathbb{E}$ suddenly change to $\mathbb{E}_{\pi'}$ in this equation?
In Sutton-Barto's book on page 63 (81 of the pdf):
$$\mathbb{E}[R_{t+1} + \gamma v_\pi(S_{t+1}) \mid S_t=s,A_t=\pi'(s)] = \mathbb{E}_{\pi'}[R_{t+1} + \gamma v_\pi(S_{t+1}) \mid S_{t} = s]$$
How does $...
- 147
2
votes
0
answers
75
views
What is the most efficient data type to store probabilities?
In ML we often have to store a huge amount of values ranging from 0 to 1, mostly being probabilities. The most common data structure to do so seems to be a floating point? Indeed, the range of ...
- 451
1
vote
1
answer
375
views
Can a variational auto-encoder learn images composed of random noise at each pixel (each drawn from the same distribution)?
Can a variational auto-encoder (VAE) learn images whose pixels have been generated from a Gaussian distribution (e.g. $N(0, 1)$), i.e. each pixel is a sample from $N(0, 1)$?
My gut feeling says no, ...
- 53
3
votes
1
answer
611
views
What is the difference between model and data distributions?
Is there any difference between the model distribution and data distribution, or are they the same?
- 394
3
votes
1
answer
107
views
What does a joint probability density function have to do with Stochastic Optimal Control and Reinforcement Learning?
I stumbled upon a job offer from a company that was looking for someone who was good with Reinforcement Learning (applied to finance) and something in their offer caught my eye. It goes something like ...
- 95
1
vote
1
answer
87
views
How can I use the success and failure data to estimate parameters of a Dirichlet distribution?
I have used Beta function to estimate the performance of the agent. I have failure and success data of the task that runs on the agent.
The parameter $\alpha$ is a number of successful tasks, while $\...
- 63