光華講壇——社會(huì)名流與企業(yè)家論壇第6867期
主題:Tensor Elliptical Graphical Model張量橢圓圖模型
主講人:南開(kāi)大學(xué)統(tǒng)計(jì)與數(shù)據(jù)科學(xué)學(xué)院 馮龍教授
主持人:統(tǒng)計(jì)與數(shù)據(jù)科學(xué)學(xué)院副院長(zhǎng) 蘭偉教授
時(shí)間:3月13日14:00-15:00
地點(diǎn):柳林校區(qū)弘遠(yuǎn)樓408會(huì)議室
主辦單位:統(tǒng)計(jì)與數(shù)據(jù)科學(xué)學(xué)院 科研處
主講人簡(jiǎn)介:
馮龍現(xiàn)任南開(kāi)大學(xué)統(tǒng)計(jì)與數(shù)據(jù)科學(xué)學(xué)院教授、博士生導(dǎo)師。國(guó)家級(jí)人才計(jì)劃入選者,南開(kāi)大學(xué)百名青年學(xué)科帶頭人。主要從事高維數(shù)據(jù)分析方面的研究,在統(tǒng)計(jì)學(xué)國(guó)際頂尖雜志JRSSB、JASA、Biometrika、Annals of Statistics、JOE、JBES等發(fā)表50余篇論文。主持一項(xiàng)天津市杰出青年基金、國(guó)家自然科學(xué)基金面上項(xiàng)目和青年項(xiàng)目。擔(dān)任Statistical Theory and Related Field副主編。
內(nèi)容提要:
We address the problem of robust estimation of sparse high dimensional tensor elliptical graphical model. Most of the research focus on tensor graphical model under normality. To extend the tensor graphical model to more heavy-tailed scenarios, motivated by the fact that up to a constant, the spatial-sign covariance matrix can approximate the true covariance matrix when the dimension turns to infinity under tensor elliptical distribution, we propose a spatial-sign-based estimator to robustly estimate tensor elliptical graphical model, the rate of which matches the existing rate under normality for a wider family of distribution, i.e. elliptical distribution. We also conducted extensive simulations and real data applications to illustrate the practical utility of the proposed methods, especially under heavy-tailed distribution.
主講人研究了稀疏高維張量橢圓圖模型的穩(wěn)健估計(jì)問(wèn)題。目前大多數(shù)研究集中在正態(tài)假設(shè)下的張量圖模型。為了將張量圖模型擴(kuò)展到更厚尾的場(chǎng)景,基于以下事實(shí):在張量橢圓分布下,當(dāng)維度趨于無(wú)窮時(shí),空間符號(hào)協(xié)方差矩陣可以在常數(shù)倍意義下逼近真實(shí)的協(xié)方差矩陣,主講人提出了一種基于空間符號(hào)的估計(jì)量來(lái)穩(wěn)健估計(jì)張量橢圓圖模型。該估計(jì)量的收斂速度與現(xiàn)有正態(tài)假設(shè)下的收斂速度相當(dāng),但適用于更廣泛的分布族,即橢圓分布。主講人還進(jìn)行了大量的模擬研究和實(shí)際數(shù)據(jù)分析,以說(shuō)明所提出方法在實(shí)際應(yīng)用中的實(shí)用性,特別是在厚尾分布下的表現(xiàn)。