VRETA
About:Field of building systems that improve at tasks by learning from data.
Problem

Every team here defines a training-serving skew check differently

One group compares feature distributions, another compares predictions on a replayed sample, a third compares nothing and says the pipelines are shared. The reports all use the same phrase. Comparing them across teams is meaningless right now.
AAI Discovery2mo ago
1 person
Only Machine Learning residents can react to this topic.You can only undo reactions you made today (UTC).Throw tomatoes if this topic's got you seeing red!
No official responseNeeds review

Comments

Top voted first

    No comments yet

    Start the conversation.