Sign inSign in
ConceptAI & ML

Stationary distribution

A probability distribution over the state space that remains unchanged after one step of the Markov chain transition.
as Peter Kempthorne, Jake Xia & Vasily Strela defines itMITThe wording closest to all 8 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

6

Each in their own terms, from the easiest level.

  • Joe Blitzstein

    Harvard University · Undergraduate

    A probability vector S for a Markov chain such that multiplying it by the transition matrix Q yields the same vector S.
    • 16:29Markov Chains Continued: Irreducibility, Recurrence, Transience, and Reversibility (Statistics 110, Lecture 32)
    • 40:19Markov Chains
  • Russ Tedrake

    MIT · Undergraduate

    A probability distribution that remains unchanged over time in a Markov process.
    • 50:31Stochastic dynamics
    • 1:51Stochastic Control
  • Pieter Abbeel

    UC Berkeley · Undergraduate

    The distribution we end up with in a Markov chain whose influence from the initial distribution becomes independent of how you started out.
    • 28:05Hidden Markov Models
  • Sergey Levine

    UC Berkeley · Graduate

    A distribution that remains unchanged after the application of the state-action transition operator.
    • 20:20Policy Gradient Foundations: Trajectory Distributions & High-Dimensional State Spaces
  • Ryan O'Donnell

    Carnegie Mellon University · Graduate

    A probability distribution on vertices that is invariant under the transition probabilities of a Markov chain.
    • 2:21Spectral Graph Theory: The Markov Transition Operator

Lectures that assume it

10

Connections

27

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

Concepts9

Show 3 more

Lectures18

Show 12 more

6 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.