Live briefing
Everything about Reparameterization trick
Technique used in stochastic gradient variational inference
The reparameterization trick is a technique used in statistical machine learning, particularly in variational inference, variational autoencoders, and stochastic optimization. It allows for the efficient computation of gradients through random variables, enabling the optimization of parametric probability models using stochastic gradient descent, and the variance reduction of estimators. Wikipedia →
🧠Start here: a 6-step reading path
- Read the overview: Reparameterization trickA 5-minute orientation
- Read the landmark paper: EEG-based motor imagery classification using convolutional neural networks with local reparameterization trickCited 44 times
- Go sideways: Evidence lower boundA closely related topic
- Go sideways: Infinitesimal strain theoryA closely related topic
đź“– Definitions
No dictionary entry for this exact phrase.
🗂️ The subject at a glance
🏆 Landmark papers (most cited)
đź“š Books worth reading
Open Library didn't respond; try again in a moment.
đź”— Related topics
- Evidence lower bound In variational Bayesian methods, the evidence lower bound (often abbreviated ELBO, also sometimes called the variational lower bound or negative variational…
- Infinitesimal strain theory In continuum mechanics, the infinitesimal strain theory is a mathematical approach to the description of the deformation of a solid body in which the displaceme…
- Stein discrepancy A Stein discrepancy is a statistical divergence between two probability measures that is rooted in Stein's method. It was first formulated as a tool to…
- Green's function for the three-variable Laplace equation In physics, the Green's function (or fundamental solution) for the Laplacian (or Laplace operator) in three variables is used to describe the response…
- Superspace Superspace is the coordinate space of a theory exhibiting supersymmetry. In such a formulation, along with ordinary space dimensions x , y , z , … {\displaystyl…
- Point estimation In statistics, point estimation involves the use of sample data to calculate a single value (known as a point estimate, since it identifies a point rather…
- Bayesian hierarchical modeling Bayesian hierarchical modelling is a statistical model written in multiple levels (hierarchical form) that estimates the posterior distribution of model…
- Stochastic gradient Langevin dynamics Stochastic gradient Langevin dynamics (SGLD) is an optimization and sampling technique composed of characteristics from Stochastic gradient descent, a…