score-based-methods-workshop.github.io - SBM @ NeurIPS

home > domains > score-based-methods-workshop.github.io

Description: A workshop to bring together researchers who use score-based methods in machine learning and statistics.

diffusion (237) score functions (2) score-based methods (2)

Example domain paragraphs

A workshop to bring together researchers who use score-based methods in machine learning and statistics.

The score function , which is the gradient of the log-density, provides a unique way to represent probability distributions. By working with distributions through score functions, researchers have been able to develop efficient tools for machine learning and statistics, collectively known as score-based methods .

Score-based methods have had a significant impact on vastly disjointed subfields of machine learning and statistics, such as generative modeling, Bayesian inference, hypothesis testing, control variates and Stein’s methods. For example, score-based generative models, or denoising diffusion models, have emerged as the state-of-the-art technique for generating high quality and diverse images. In addition, recent developments in Stein’s method and score-based approaches for stochastic differential equations (S

Links to score-based-methods-workshop.github.io (8)

• latentspace.cc Arash Vahdat - Latent Space
• karstenkreis.github.io Karsten Kreis
• yang-song.github.io Yang Song
• yang-song.net Yang Song
• ghliu.github.io Guan-Horng Liu
• voletiv.github.io Vikram Voleti
• arashvahdat.com Arash Vahdat - Latent Space
• luchengthu.github.io Cheng Lu