arXiv (Cornell University) · 2020 · 15 citations · 26 references
ComputingComputer ScienceMathematicsAlgorithmsMachine LearningOptimizationKernel MethodsNumerical AlgorithmsOptimization For Machine LearningParticle MethodsStatistical InferenceVariational OptimizationAsymptotic AnalysisConvergenceDivergenceDivergence MinimizationFinite TimeGradient DescentStochastic Gradient Descent
We study the Stein Variational Gradient Descent (SVGD) algorithm, which optimises a set of particles to approximate a target probability distribution $π\propto e^{-V}$ on $\mathbb{R}^d$. In the population limit, SVGD performs gradient descent in the space of probability distributions on the KL divergence with respect to $π$, where the gradient is smoothed through a kernel integral operator. In this paper, we provide a novel finite time analysis for the SVGD algorithm. We provide a descent lemma establishing that the algorithm decreases the objective at each iteration, and rates of convergence for the average Stein Fisher divergence (also referred to as Kernel Stein Discrepancy). We also provide a convergence result of the finite particle system corresponding to the practical implementation of SVGD to its population version.
26
Advances in Variational Inference
Cheng Zhang, Judith Bütepage, Hedvig Kjellström et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2018 · 654 citations · Full text