AI Regulations in China
AI Regulations in the European Union (EU)
AI Regulations in the US
AI Regulations in India
Model safety
Synthetic & Generative AI
MLOps
Model Performance
ML Monitoring
Explainable AI

Wasserstein distance

The Wasserstein distance is a distance function for measuring the distance between two probability distributions.

Also known as the Earth Mover’s distance, the metric It is defined as the minimum amount of "energy cost" required to transform one distribution into the other. 

It is calculated as:

W:= W(FP,FQ) = (01 ∣FP−1(u) − FQ−1(u) ∣2 du)1/2

Where, 

P and Q = two different conditions 

FP and FQ = corresponding cumulative distribution functions (CDFs)

FP−1 and FQ−1   = quantile functions

The Wasserstein distance has several advantages, such as the ability to take into account the geometry of the space in which the distributions are defined and the ability to handle distributions with different support sizes.

Wasserstein distance is used for numerical features. The default threshold in AryaXAI is 0.05.

Liked the content? you'll love our emails!

Thank you! We will send you newest issues straight to your inbox!
Oops! Something went wrong while submitting the form.

See how AryaXAI improves
ML Observability

Learn how to bring transparency & suitability to your AI Solutions, Explore relevant use cases for your team, and Get pricing information for XAI products.