BriefGPT.xyz
Jun, 2024
胜者通吃学习者是几何感知条件密度估计器
Winner-takes-all learners are geometry-aware conditional density estimators
HTML
PDF
Victor Letzelter, David Perera, Cédric Rommel, Mathieu Fontaine, Slim Essid...
TL;DR
使用Winner-takes-all学习算法进行条件密度估计，利用其几何特性优势，通过量化和密度估计实现了竞争力的结果。
Abstract
winner-takes-all training
is a simple learning paradigm, which handles
ambiguous tasks
by predicting a set of plausible hypotheses. Recently, a connection was established between
→