講座主題：Stein variational gradient descent with local approximations
專家姓名：閆亮
工作單位：東南大學(xué)
講座時(shí)間：2021年12月16日 9:00-10:00
講座地點(diǎn)：騰訊會(huì)議，會(huì)議ID：403792057
主辦單位：煙臺(tái)大學(xué)數(shù)學(xué)與信息科學(xué)學(xué)院
內(nèi)容摘要：
Bayesian computation plays an important role in modern machine learning and statistics to reason about uncertainty. A key computational challenge in Bayesian inference is to develop efficient techniques to approximate, or draw samples from posterior distributions. Stein variational gradient decent (SVGD) has been shown to be a powerful approximate inference algorithm for this issue. However, the vanilla SVGD requires calculating the gradient of the target density and cannot be applied when the gradient is unavailable or too expensive to evaluate. In this talk, we explore one way to address this challenge by the construction of a local surrogate for the target distribution in which the gradient can be obtained in a much more computationally feasible manner. More specifically, we approximate the forward model using a deep neural network (DNN) which is trained on a carefully chosen training set, which also determines the quality of the surrogate. To this end, we propose a general adaptation procedure to refine the local approximation online without destroying the convergence of the resulting SVGD. This significantly reduces the computational cost of SVGD and leads to a suite of algorithms that are straightforward to implement. The new algorithm is illustrated on a set of challenging Bayesian inverse problems, and numerical experiments demonstrate a clear improvement in performance and applicability of standard SVGD.
主講人介紹：
閆亮，東南大學(xué)副教授、博士生導(dǎo)師。主要從事不確定性量化、貝葉斯反問(wèn)題理論與算法的研究。2018年入選東南大學(xué)“至善青年學(xué)者”（A層次）支持計(jì)劃，2017年入選江蘇省高校“青藍(lán)工程”優(yōu)秀青年骨干教師培養(yǎng)對(duì)象。目前主持國(guó)家自然科學(xué)基金面上項(xiàng)目?jī)身?xiàng)，主持完成國(guó)家自然科學(xué)基金青年項(xiàng)目和江蘇省自然科學(xué)基金青年項(xiàng)目各一項(xiàng)。已經(jīng)在《SIAM J. Sci. Comput.》、《Inverse Problems》、《J. Comput. Phys.》等國(guó)內(nèi)外刊物上發(fā)表30多篇學(xué)術(shù)論文.
