Questions tagged [wasserstein]

The Wasserstein metric or Earth Movers Distance is a distance function between probability distributions.

Filter by
Sorted by
Tagged with
0 votes
0 answers
5 views

how to solve for wasserstein duality easily in a special case when 2-Wasserstein inequality constraint is binding

I was going through this nice paper ” A Simple and General Duality Proof for Wasserstein Distributionally Robust Optimization”, and one quick qu on applying Theorem 1 to my poject: What if in my ...
numpynp's user avatar
  • 21
0 votes
0 answers
21 views

What are the most common information matrices in statistics and machine learning? [closed]

The Fisher information matrix is extremely popular in information theory, probability, machine learning, and statistics. I recently came across another information matrix, the Wasserstein information ...
Info's user avatar
  • 1
0 votes
0 answers
9 views

Proof for equivalence definition of convergence in the Wasserstein space

From "An Invitation to Statistics in Wasserstein Space" (Victor M. Panaretos and Yoav Zemel) Theorem 2.2.1 (Convergence in Wasserstein Space) Let $\mu, \mu_n \in \mathscr{W}_p(\mathscr{X})$. ...
Eryna's user avatar
  • 309
0 votes
0 answers
86 views

Does Sliced Wasserstein Distance assume that the two distributions are zero-mean?

Sliced Wasserstein distance (SWD) depends on Radon transform, which is defined as $\mathbb{R}I(t,\theta) = \int \delta(t-\theta^Tx)I(x) \, dx$. The definition of SWD, however, does not use the ...
rando's user avatar
  • 236
0 votes
0 answers
64 views

What metrics could I use to compare multiple 2-dimensional histograms/sinograms?

I have a set of two-dimensional shapes, each represented by one or more closed paths, which enclose one continuous area. My objective is to establish a measure of similarity between these shapes. I do ...
Dugnom's user avatar
  • 101
0 votes
0 answers
31 views

How to quantify the dissimilarity across different types of variables?

I have two dataframes with the same columns but with varying sample sizes. I want to compare corresponding columns for homogeneity (i.e., do they come from the same distribution?). There are different ...
Glue's user avatar
  • 433
1 vote
0 answers
16 views

How to apply a seasonal index into an eCDF?

I am doing a Before/After analysis, which is aiming at evaluating the effect of a change. Assume I have made a change at the beginning of June-2022, and I want to evaluate the effect of the change ...
Mostafa's user avatar
  • 111
1 vote
0 answers
110 views

Wasserstein-1 distance between two joint distributions

Let me define random variables $A, B, C, D$ that are independent of each other. Additionally, PDFs of $A, B$ are the same, and PDFs of $C, D$ are the same too In such a case, is the following correct? ...
deeperson's user avatar
1 vote
2 answers
635 views

Normalized Wasserstein distance

The wasserstein_distance will be smaller the longer u_values and v_values are. ...
HappyPy's user avatar
  • 133
2 votes
0 answers
121 views

Why is the Wasserstein distance not used in Variational Inference

I just started learning the concept of variational inference in the context of variational Autoencoder, so please excuse me if the answer is obvious. I would like to know why traditionally, KL-...
user3748950's user avatar
2 votes
1 answer
453 views

GAN : Why does a perfect discriminator mean no gradient for the generator?

(Note : this is a cross-post from Artificial Intelligence. As I got no answer there in two weeks, I'm trying my luck on a more popuplated SE site. I know this is against SE's policy on cross-posting ...
Soltius's user avatar
  • 1,184
2 votes
0 answers
33 views

How to calculate the max possible earth mover distance between histograms, given the buckets?

I have two histograms and am able to calculate the EMD / Wasserstein metric between them using the algorithm described here. In order to better communicate the implication of this metric, I want to ...
user12138762's user avatar
1 vote
1 answer
309 views

Earth Mover (Wasserstein) distance for ordinal discrete data

I am doing data analysis for my Masters research and which includes some Likert scale type questions. I have been calculating some distances between the responses for these questions. All this has ...
anna6931's user avatar
  • 101
0 votes
0 answers
41 views

Is there a functionality that gets pairwise distance with metric as wasserstein distance

I understand that there is a implementation in scipy for two 1-D matrixes, but what i need is a fast implementation for pairwise vectors in a 2D vector, like this https://scikit-learn.org/stable/...
repsick3r's user avatar
3 votes
1 answer
464 views

Is there an R or python package to calculate wasserstein metric between negative binomial distributions?

As the title says I am looking for an R or python package which can calculate wasserstein distance (aka earthmovers distance between) two lists (vectors) of sampled values from a negative binomial ...
Angus Campbell's user avatar
0 votes
0 answers
18 views

Transform Earth mover's distance/Wasserstein metric to percentance (0 to 1 or 0% to 100%) [duplicate]

Ok, I do some calculations between binned histograms via the use of Wasserstein metric and more specifically this python library.. https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats....
just_learning's user avatar
1 vote
0 answers
61 views

Can I adjust the Wasserstein GAN loss function for my particular data?

I am working on building Generative Adversarial Networks for the purpose of generating synthetic flight data. The GAN will be trained on actual time-series flight data in the form of a (n,m,9) array ...
ScubaNinjaDog's user avatar
0 votes
0 answers
211 views

Wasserstein distance between multivariate lognormal distributions

Wikipedia gives the following formula for normal distributions: What changes, if any, do I need to make to handle multivariate lognormal distributions instead?
Roman's user avatar
  • 33
0 votes
0 answers
257 views

I need help understanding the meaning of the loss values of a WGAN with Gradient Penalty

I am currently working on training a Auxiliary Classifier Wasserstein GAN with Gradient Penalty. I based my implementation off of https://keras.io/examples/generative/wgan_gp/ (to which I added the ...
Moritz Grünbauer's user avatar
4 votes
1 answer
1k views

Wasserstein distance and Kolmogorov-Smirnov statistic as measures of effect size

So I've been dealing with 2 sample hypothesis testing with very large samples (around 20,000s each). Whenever I test for the equality of distribution I always reject the null hypothesis, even though ...
Girigio's user avatar
  • 53
0 votes
0 answers
79 views

Measure for evaluating a density estimation procedure

Given an implementation of a multivariate density estimation scheme, what would be a suitable measure to evaluate the accuracy of the procedure? I am currently evaluating the procedure using three ...
Eike P.'s user avatar
  • 2,126
0 votes
0 answers
280 views

Interpretation of upper bound on the Wasserstein Distance

I am trying to interpret the 2-Wasserstein distance and the upper bound on it. Let's say I have 2-Wasserstein distance between two distributions to be $x$, and I have an upper bound on it which gives ...
newbie's user avatar
  • 215
2 votes
1 answer
966 views

Intuition on Wasserstein Distance

I've been trying to familiarize myself with the Wasserstein distance and saw this answer on StackExchange by @antike that at first made a lot of sense, but then it didn't (to me, of course). In the ...
Optimesh's user avatar
  • 173
0 votes
1 answer
166 views

How can one compute the "average" of a dataset of histograms that minimizes the mean Earth Mover's Distance between all data points and average?

It is my understanding that when the distance metric is euclidean distance, the mean of a dataset minimizes the average distance between all data points and the computed "mean". In the case ...
mcguiremichael's user avatar
1 vote
0 answers
39 views

What is this probability distribution?

Thank you in advance for any suggestions or feedback. I have a discrete 1D probability distribution represented as a vector $\textbf{p}$, $p_i = p(x_i)$. I am interested in finding the Wasserstein (...
user979797987678's user avatar
1 vote
1 answer
1k views

When is my Wasserstein GAN-GP overfitting?

I have a hard time interpreting the WGAN-GP losses attached. At which epoch is D and/or G overfitting? The quality improves a lot overtime, yet the generator loss at later epochs does not appear on ...
Science_Cattie's user avatar
0 votes
0 answers
725 views

Wasserstein distance for categorical data? Relationship to TVD?

Is the Wasserstein distance applicable for categorical data? e.g. if we have the distribution of different coloured balls in two bags, ...
Anonymous Scientist's user avatar
1 vote
0 answers
129 views

Reference for Wasserstein distance for generalized exponential family and generalized extreme value probability distributions

The Wikipedia page gives the analytical results for computing the Wasserstein metric between two multivariate normal distributions, and I thought it used to give results for several other commonly ...
wdkrnls's user avatar
  • 297
-1 votes
1 answer
93 views

K-Lipschitz for the Wasserstein GANs

I am trying to follow this blog for Wasserstein loss for Generative Adversarial Networks: From GAN to WGAN. Actually, I am trying to follow the logic behind the K-Lipschitz continuity. This post in ...
Jose Ramon's user avatar
1 vote
1 answer
54 views

How to check whether a partitioning is more balanced?

For example consider the following two partitions that add approximately to 100 percent. Partition 1 : 41% 36% 14% 5% 2% 1% <1% <1% Partition 2 : 82% 10% 4% 3% <1% <1% <1% <1% ...
Hakan Baba's user avatar
0 votes
0 answers
77 views

Horizontal vs Vertical optimal transport of probability distributions

Optimal transport has a primal and dual form. My question is: Is the primal formulation of OT intended for horizontal movement of probability mass, whereas the dual formulation is more geared towards ...
develarist's user avatar
  • 3,481
0 votes
0 answers
228 views

Does Wasserstein distance require the source and target distributions to have the same mass?

If we minimize the Wasserstein loss, $$W_1 (P_S, P_T) = \underset{\gamma \in \Pi}{\text{min }} \sum_{x,y} |x-y|\gamma(x,y)$$ which means we are looking for the coupling $\gamma(x,y)$ that minimizes ...
develarist's user avatar
  • 3,481
1 vote
0 answers
207 views

Properties of Sinkhorn distance

I am reading the paper by Cuturi http://www.marcocuturi.net/Papers/cuturi13sinkhorn.pdf and I am curious about the properties of Sinkhorn distance and wondering what properties of the Sinkhorn ...
Arijit Sehanobish's user avatar
6 votes
1 answer
3k views

What is the intuitive difference between Wasserstein-1 distance and Wasserstein-2 distance?

What is the intuitive difference between Wasserstein-1 distance and Wasserstein-2 distance, and how to know which one to use?
develarist's user avatar
  • 3,481
1 vote
1 answer
4k views

What are the advantages of Wasserstein distance compared to Jensen-Shannon divergence?

What is the practical difference between Wasserstein metric and Jensen-Shannon divergence? Wasserstein metric is also referred to as Earth mover's distance. From Wikipedia: Wasserstein metric is a ...
develarist's user avatar
  • 3,481
2 votes
0 answers
150 views

How to Show Wasserstein Metric is Sum Invariant?

A paper I'm trying to understand states that that Wasserstein metric obeys certain properties, which I'd like to prove. This metric is defined for two random variables $U, V$ and $p \in (1, \infty)$ ...
Rylan Schaeffer's user avatar
8 votes
1 answer
3k views

Multivariate Wasserstein metric for $n$-dimensions

I am a vegetation ecologist and poor student of computer science who recently learned of the Wasserstein metric. Application of this metric to 1d distributions I find fairly intuitive, and inspection ...
kdoherty's user avatar
1 vote
1 answer
597 views

Optimal critic in Wasserstein GAN (WGAN)

In the Wasserstein GAN (generative adversarial network) paper they say that the critic needs to be optimal. What does this mean practically? They do more training iterations of critic (5) than the ...
KFa's user avatar
  • 43
1 vote
0 answers
562 views

Weight Clipping range with WGAN and relation with other factors

For a while, my code with WGAN has failed to generate quality images through a complicated multi-class database. My issue has been with implementation and not code. Recently I read the WGAN-GP paper ...
Mr. Johnny Doe's user avatar
0 votes
1 answer
155 views

Large gradient magnitude in WGAN-GP

I've implemented a minimal WGAN-GP on MNIST (code here).it kinda works and outputs some digits but loss/gradient magnitudes are so huge, for example: $GradientPenalty \approx 10^{19}$ $D(\hat{x})- D(...
AmirHossein's user avatar
4 votes
1 answer
905 views

Upper Bound on the Wasserstein Distance

I'm interested to know if it's possible to construct an upper bound on the Wasserstein distance in terms of the Kolgomorov distance. The Wasserstein distance can we written as $$W_{1}\left(F, G\...
doug's user avatar
  • 319
3 votes
1 answer
2k views

Why is "weight clipping" needed for Wasserstein GANs?

I am reading the original paper on the Wasserstein GAN: https://arxiv.org/pdf/1701.07875.pdf and I came across this paragraph: I don't understand the statement: "$\mathcal{W}$ is compact implies ...
Frederic Chopin's user avatar
1 vote
0 answers
50 views

Statistical estimators distance for close empirical distributions

Is it valid to argue that two empirical distributions $ p_1, p_2 $ having small Wasserstein distance $W_r(\cdot)$ for an order $ r $ will yield close MLE estimators for a statistical model ...
Dion's user avatar
  • 944
1 vote
0 answers
421 views

Wasserstein distance / EMD of two sets of 2D weighted points?

I am trying to implement a 2D version of the EMD/Wasserstein Distance to measure the distance of sets of 2D weighted points. Let $A = \{a_{1}, a_{2}, ..., a_{m}\}$, be a weighted point set such that $...
Luca Angioloni's user avatar
9 votes
2 answers
3k views

Relation Between Wasserstein Distance and KL-Divergence (Relative Entropy)

Consider the Wasserstein metric of order one $W_1$ (a.k.a. the Earth Movers Distance). I would like to know whether it is possible to link $W_1$ and Kullback–Leibler divergence (a.k.a. relative ...
JohnS's user avatar
  • 91
9 votes
3 answers
9k views

Calculate Earth Mover's Distance for two grayscale images

I am trying to calculate EMD (a.k.a. Wasserstein Distance) for these two grayscale (299x299) images/heatmaps: Right now, I am calculating the histogram/distribution of both images. The histograms ...
LVDW's user avatar
  • 155
7 votes
1 answer
3k views

Earth Movers Distance and Maximum Mean Discrepency

By Kantorovich-Rubinstein duality the Earth Movers Distance (EMD)/Wasserstein Metric is equivalent to Maximum Mean Discrepancy (MMD) correct? See here for a more thorough explanation. Why then does ...
www3's user avatar
  • 671
2 votes
1 answer
192 views

Prerequisites for Wasserstein GAN/Autoencoder

Can someone who read WGAN/WAE papers and understood Wasserstein part, could you share how you prepared necessary Optimal Transport background? The mentioned papers seem little tough if you don't have ...
Jakub Bartczuk's user avatar
4 votes
1 answer
252 views

Computing Wasserstein Distance

For two probability measures $\mu$ and $\nu$, the Wassertein Distance is defined as $$W_p (\mu , \nu) = \left[ \inf\limits_{\gamma \in \Gamma} |x-y|^p \, d\gamma (x,y) \right] ^{\frac{1}{p}} \, , $$ ...
Amir Sagiv's user avatar
1 vote
1 answer
348 views

Implementation of WAE-GAN does not match with the description in the paper

According to the litterature and specifically to this paper, the wasserstein autoencoders is an encoder-decoder architecture. So it must contain encoder and decoder parts. in the algorithm ...
Emna Jaoua's user avatar