Sign inSign in
ConceptAI & ML

Sample complexity

The number of samples required by an algorithm to achieve a certain level of performance with high probability.
as Sergey Levine defines itUC BerkeleyThe wording closest to all 4 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.

Empirical error1Estimation1Probability1Probability bounds1Reinforcement learning1Reinforcement learning algorithms1Risk minimization1Statistical learning1

Opens up

Concepts that name this one as a prerequisite.

Lecturers

4

Each in their own terms, from the easiest level.

  • Shahar Mendelson

    Texas A&M University · Graduate

    The cardinality of the sample needed to ensure a desired accuracy with a given high probability.
    • 25:10AI in Science and Engineering: The Role of Academia in Understanding AI
  • Nika Haghtalab

    UC Berkeley · Graduate

    The number of samples and the quality of the estimator needed to achieve convergence in the game-playing dynamics.
    • 20:59Multi-objective Learning: An Algorithmic Toolbox for Optimal Predictions Anytime Anywhere
  • Andrea Zanette

    UC Berkeley · Graduate

    The number of samples an algorithm needs to achieve a desired level of performance.
    • 24:45Towards a Statistical Foundation for Reinforcement Learning

Lectures that assume it

2

Connections

13

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

4 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.