Sign inSign in
ConceptAI & ML

Langevin dynamics

A stochastic process combining gradient updates with added Gaussian noise to model the trajectory of weights in noisy optimization.
as Anvith Thudi 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.

  • Stefano Ermon

    Stanford University · Graduate

    An MCMC algorithm that samples from a distribution by following the gradient of the log-density while adding Gaussian noise to explore the space.
    • 41:16Generative Modeling by Estimating Gradients of the Data Distribution
  • Hugo Touchette

    International Centre for Theoretical Physics · Graduate

    A stochastic differential equation describing the motion of a particle subject to deterministic forces like drag and spring forces, alongside random noise.
    • 20:51Introduction to Large Deviation Theory

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.