Sign inSign in
ConceptAI & ML

Sufficient statistic

A statistic ss is sufficient for distinguishing two hypotheses if the likelihood ratio depends on the underlying model only through ss.
as Ryoto Koike defines itGoogle Research & TechTalksThe wording closest to all 3 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

3

Each in their own terms, from the easiest level.

  • David Silver

    Google DeepMind · Introductory

    A state that fully characterizes the distribution over future actions, observations, and rewards without needing the underlying history.
    • 44:04Introduction to Reinforcement Learning
  • Russ Tedrake

    MIT · Graduate

    A statistic that has all the information needed about the parameter of interest that is contained in the sample.

Lectures that assume it

1

Connections

9

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

3 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.