Finite-Particle Rates for Regularized Stein Variational Gradient Descent
有限粒子率的正则化Stein变分梯度下降
机构 * Department of Mathematics, Georgia Institute of Technology(佐治亚理工学院数学系) ; Department of Statistics, University of California, Davis(加州大学戴维斯分校统计系) ; Department of Statistics and Operations Research, University of North Carolina, Chapel Hill(北卡罗来纳大学夏洛特分校统计与运筹学系) ; Department of Statistics, University of Chicago(芝加哥大学统计系)
AI总结 本文研究了正则化Stein变分梯度下降算法的有限粒子率,通过应用树脂型预条件器来校正SVGD的常数阶偏差,推导了时间平均经验测度的非渐近界,并在目标满足W₁I条件下,证明了对于光滑核函数的大类,W₁收敛。