Sign inSign in
ConceptAI & ML

Distribution shift

A change in the data distribution between the training phase and the inference/test phase.
as Sara Beery defines itMITThe wording closest to all 5 definitions
Watch it explained

Know first

Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.

Opens up

Concepts that name this one as a prerequisite.

Lecturers

5

Each in their own terms, from the easiest level.

  • Sasha Rush

    Cornell University · Graduate

    Actual mistakes deviating from training examples during reinforcement learning for model correction.
    • 40:02Speculations on Test-Time Scaling for Large Language Models (o1)
  • Sergey Levine

    UC Berkeley · Graduate

    The problem where a model is trained on one particular distribution and then needs to perform well under a different distribution.
    • 30:06Offline Reinforcement Learning
  • Andrea Zanette

    UC Berkeley · Graduate

    The mismatch between the state-action distribution present in a historical dataset and the distribution induced by the target optimal policy.
    • 39:10Towards a Statistical Foundation for Reinforcement Learning
  • Russ Tedrake

    MIT · Graduate

    Distribution shift occurs when a closed-loop policy drifts away from the training data distribution, leading to compounding errors.
    • 1:02:18Imitation Learning, Foundation Models, and Course Wrap-up

Lectures that assume it

3

Connections

17

The lectures that define it or assume it, and the concepts next to it.

5 lecturers. Definitions are written by AI from each lecture’s transcript. A time with a play mark starts the lecture at the moment the lecturer says it.