Candidate set sampling: A note on theoretical guarantees
By: Shifeng Xiong
In this note we introduce a simple numerical sampling method, called candidate set sampling, which is based on an straightforward discretization to the density function. This method requires the knowledge of the density function (up to an unknown normalizing constant) only. Furthermore, candidate set sampling is non-iterative, dimension-free, and easy to implement, with fast convergence and low computational cost. We present its basic convergence properties in the note.
Similar Papers
Systematic Alias Sampling: an efficient and low-variance way to sample from a discrete distribution
Data Structures and Algorithms
Makes computers pick random numbers much faster.
Finite-Sample Valid Rank Confidence Sets for a Broad Class of Statistical and Machine Learning Models
Methodology
Figures out how sure we are about rankings.
Finite-Sample Valid Rank Confidence Sets for a Broad Class of Statistical and Machine Learning Models
Methodology
Figures out how sure we are about rankings.