1. K

    Updating covariance matrix when more info becomes available.

    Say, I have a solution to a 3D problem in the form of a a triple (x0,y0,z0) with uncertainty specified by an error covariance matrix S. Using these one can calculate and plot say the 1 sigma ellipsoid around this solution. Now suppose someone tells me that my solution "z=z0" is in fact...
  2. P

    Incremental update to *existing* Logistic Regression model?

    Hi, In our work, we have a large-scale logistic regression model we hate to train everyday. Is there a way we can somehow update the existing model with the new day's data? Currently, we re-train the model daily with the past ninety-day (sliding window) data. And we use the L1-regularizer...