Skip to main content
Data Science

Return to Question

improved formatting
Source Link
edit approved Oct 18, 2016 at 15:44
Abhishek
edit approved Oct 18, 2016 at 15:44
Abhishek
  • 2k
  • 3
  • 15
  • 21

Background: The basic set-up for non-negative matrix factorization, nmfnon-negative matrix factorization (nmf), is that we take a matrix with non-negative elements, X and find two other non-negative matrices H and T such that $||X - HT||$ is a minimum.

$||X - HT||$ is a minimum

$X$ in this example is a matrix that represents a data set. Rows correspond to samples of data, and columns correspond to features. I understand that nmfnmf is used for feature reduction. My understanding is that you can use the latent features to train a model on. 

However, suppose that I use nmf for feature reduction and then get a new row of data and want to find the reduced features for the new data. Do I have to run nmf again with an updated dataset and then retrain my model each time?

Background: The basic set-up for non-negative matrix factorization, nmf, is that we take a matrix with non-negative elements, X and find two other non-negative matrices H and T such that $||X - HT||$ is a minimum. $X$ in this example is a matrix that represents a data set. Rows correspond to samples of data, and columns correspond to features. I understand that nmf is used for feature reduction. My understanding is that you can use the latent features to train a model on. However, suppose that I use nmf for feature reduction and then get a new row of data and want to find the reduced features for the new data. Do I have to run nmf again with an updated dataset and then retrain my model each time?

Background: The basic set-up for non-negative matrix factorization (nmf), is that we take a matrix with non-negative elements, X and find two other non-negative matrices H and T such that

$||X - HT||$ is a minimum

$X$ in this example is a matrix that represents a data set. Rows correspond to samples of data, and columns correspond to features. I understand that nmf is used for feature reduction. My understanding is that you can use the latent features to train a model on. 

However, suppose that I use nmf for feature reduction and then get a new row of data and want to find the reduced features for the new data. Do I have to run nmf again with an updated dataset and then retrain my model each time?

Bumped by Community user
Bumped by Community user
Bumped by Community user
Bumped by Community user
Bumped by Community user
Source Link
sebastianspiegel
sebastianspiegel
  • 921
  • 4
  • 11
  • 16

How do I get latent features for a new row of data when doing non-negative matrix factorization?

Background: The basic set-up for non-negative matrix factorization, nmf, is that we take a matrix with non-negative elements, X and find two other non-negative matrices H and T such that $||X - HT||$ is a minimum. $X$ in this example is a matrix that represents a data set. Rows correspond to samples of data, and columns correspond to features. I understand that nmf is used for feature reduction. My understanding is that you can use the latent features to train a model on. However, suppose that I use nmf for feature reduction and then get a new row of data and want to find the reduced features for the new data. Do I have to run nmf again with an updated dataset and then retrain my model each time?