應(yīng)yl7703永利官網(wǎng)邀請(qǐng)，中國(guó)人民大學(xué)朱利平教授、浙江大學(xué)張立新教授、華東師范大學(xué)於州教授、北京師范大學(xué)郭旭教授和西安交通大學(xué)朱學(xué)虎教授等將于2024年8月19日-21日訪問蘭州大學(xué)，期間舉辦專題討論，歡迎全校師生參加。

報(bào)告時(shí)間：2024年8月20日(星期二) 08:30開始

報(bào)告地點(diǎn)：理工樓631

報(bào)告1：SLICED INDEPENDENCE TEST

報(bào)告人：朱利平教授

摘要：An ideal independence test should possess three properties: it should be zero-independence equivalent, numerically efficient, and asymptotically normal. We introduce a slicing procedure for estimating a popular measure of nonlinear dependence, leading to the resultant sliced independence test simultaneously possessing all three properties. In addition, the power performance of the sliced independence test improves as the number of observations within each slice increases. The popular rank test corresponds to a special case of the sliced independence test that contains two observations within each slice. The sliced independence test is thus more powerful than the rank test. The size performance of the sliced independence test is insensitive to the number of slices, in that the slicing estimation is consistent and asymptotically normal for a wide range of slice numbers. We further adapt the sliced independence test to account for the presence of multivariate control variables. The theoretical properties are confirmed using comprehensive simulations and an application to an astronomical data set.

報(bào)告人簡(jiǎn)介：朱利平，中國(guó)人民大學(xué)長(zhǎng)聘教授、博士生導(dǎo)師，學(xué)校和理工學(xué)部學(xué)術(shù)委員會(huì)委員，統(tǒng)計(jì)與大數(shù)據(jù)研究院院長(zhǎng)，人民教育出版社普通高中教科書《數(shù)學(xué)》聯(lián)合主編，國(guó)家重大人才工程入選者，國(guó)家杰出青年科學(xué)基金獲得者，國(guó)家重點(diǎn)研發(fā)計(jì)劃首席科學(xué)家，兼任中國(guó)現(xiàn)場(chǎng)統(tǒng)計(jì)研究會(huì)生存分析分會(huì)理事長(zhǎng)和高維數(shù)據(jù)統(tǒng)計(jì)分會(huì)副理事長(zhǎng)等。先后受邀擔(dān)任國(guó)際統(tǒng)計(jì)學(xué)領(lǐng)域頂級(jí)學(xué)術(shù)期刊《統(tǒng)計(jì)年刊》、國(guó)際權(quán)威學(xué)術(shù)期刊《中華統(tǒng)計(jì)學(xué)》和《多元分析》等副主編，以及國(guó)內(nèi)統(tǒng)計(jì)學(xué)領(lǐng)域頂級(jí)學(xué)術(shù)期刊《中國(guó)科學(xué)·數(shù)學(xué)》（中、英文版）、《系統(tǒng)科學(xué)與數(shù)學(xué)》（中、英文版）和《應(yīng)用概率統(tǒng)計(jì)》等青年編委、編委和副主編等。長(zhǎng)期從事大數(shù)據(jù)統(tǒng)計(jì)學(xué)基礎(chǔ)理論、方法和應(yīng)用研究。1.在高維度大數(shù)據(jù)領(lǐng)域，提出不依賴于切片數(shù)的累積切片估計(jì)方法、不依賴于分布條件的半?yún)?shù)降維方法和不依賴于模型的變量篩選方法，解決了充分降維領(lǐng)域“公開問題”，被認(rèn)為是該領(lǐng)域“突破性進(jìn)展”，被列為變量篩選領(lǐng)域“基準(zhǔn)方法”。2.在非線性大數(shù)據(jù)領(lǐng)域，提出投影相關(guān)系數(shù)度量非線性相關(guān)關(guān)系，廣泛應(yīng)用于類腦科學(xué)和天文學(xué)等研究中；原創(chuàng)性提出區(qū)間分位數(shù)相依基本思想，擴(kuò)寬了（分布）獨(dú)立基本概念并建立了（分布）獨(dú)立與分位數(shù)獨(dú)立和均值獨(dú)立的聯(lián)系。3.在大數(shù)據(jù)應(yīng)用領(lǐng)域，主持開發(fā)的虛假訴訟預(yù)警甄別系統(tǒng)已經(jīng)在四川省高級(jí)人民法院和成都市中級(jí)人民法院等10家法院部署應(yīng)用示范，參與編寫的人民法院信息化標(biāo)準(zhǔn)《民事案件信息技術(shù)規(guī)范》已被最高人民法院發(fā)布實(shí)施。

報(bào)告2：Response-Adaptive Randomization in Clinical Trials

報(bào)告人：張立新教授

摘要：In clinical trial studies, adaptive randomization is a popular method to randomize patients to treatments. Response-adaptive designs are adaptive schemes to randomize treatments to patients with allocation probabilities depending on the results of previous assignments and treatment outcomes. The adoption of response-adaptive designs has proved to be beneficial to researchers, by providing more efficient clinical trials, and to patients, by increasing the likelihood of receiving better treatment. In this talk, we discuss the several classes of response-adaptive randomization procedures in the view of asymptotic statistical efficiency.

報(bào)告人簡(jiǎn)介：浙江工商大學(xué)特聘教授、校學(xué)術(shù)委員會(huì)委員，浙江大學(xué)求是特聘教授。1995年獲復(fù)旦大學(xué)理學(xué)博士學(xué)位，1997年晉升為教授，2001年起先后擔(dān)任浙江大學(xué)統(tǒng)計(jì)學(xué)研究所副所長(zhǎng)、常務(wù)副所長(zhǎng)、所長(zhǎng)，浙江大學(xué)數(shù)學(xué)系副主任、數(shù)學(xué)科學(xué)學(xué)院副院長(zhǎng)?，F(xiàn)任浙江大學(xué)數(shù)據(jù)科學(xué)研究中心副主任、中國(guó)現(xiàn)場(chǎng)統(tǒng)計(jì)研究會(huì)常務(wù)理事、浙江省現(xiàn)場(chǎng)統(tǒng)計(jì)研究會(huì)理事長(zhǎng)。主要從事臨床試驗(yàn)自適應(yīng)隨機(jī)化設(shè)計(jì)、概率極限理論、相依數(shù)據(jù)模型等領(lǐng)域的研究，發(fā)表了學(xué)術(shù)論文180余篇，先后主持國(guó)家自然科學(xué)基金面上項(xiàng)目5項(xiàng)、杰出青年基金項(xiàng)目1項(xiàng)、重點(diǎn)項(xiàng)目1項(xiàng)、聯(lián)合基金重點(diǎn)項(xiàng)目一項(xiàng)，于2008年入選教育部“新世紀(jì)優(yōu)秀人才支持計(jì)劃”，2018年或2016-2018浙江省“三育人”先進(jìn)個(gè)人和浙江大學(xué)第九屆“三育人”標(biāo)兵，2019年入選浙江省科技創(chuàng)新領(lǐng)軍人才，2020年當(dāng)選Institute of Mathematical Statistics Fellow。

報(bào)告3：Random Forests and Deep Neural Networks for Euclidean and Non-Euclidean regression

報(bào)告人：於州教授

摘要：Neural networks and random forests are popular and promising tools for machine learning. We explore the proper integration of these two approaches for nonparametric regression to improve the performance of a single approach. It naturally synthesizes the local relation adaptivity of random forests and the strong global approximation ability of neural networks. By utilizing advanced U-process theory and an appropriate network structure, we obtain the minimax convergence rate for the estimator. Moreover, we propose the novel random forest weighted local Frechet regression paradigm for regression with Non-Euclidean responses. We establish the consistency, rate of convergence, and asymptotic normality for the Non-Euclidean random forests based estimator.

報(bào)告人簡(jiǎn)介：於州，華東師范大學(xué)教授、博士生導(dǎo)師，統(tǒng)計(jì)學(xué)院副院長(zhǎng)。主要研究方向?yàn)楦呔S數(shù)據(jù)統(tǒng)計(jì)分析及統(tǒng)計(jì)機(jī)器學(xué)習(xí)，在Annals of Statistics，Biiometrika，JASA，JRSSB，Journal of Machine Learning Research，IEEE Information Theory等知名統(tǒng)計(jì)及機(jī)器學(xué)習(xí)期刊上發(fā)表論文50余篇。曾主持國(guó)家重點(diǎn)研發(fā)計(jì)劃課題、自然科學(xué)基金青年、面上項(xiàng)目，獲得上海市自然科學(xué)二等獎(jiǎng)等獎(jiǎng)項(xiàng)，霍英東青年科學(xué)獎(jiǎng)二等獎(jiǎng)。并先后入選上海高校東方學(xué)者特聘教授，上海市青年拔尖人才，上海市青年科技啟明星及國(guó)家青年人才計(jì)劃。

報(bào)告4：Model-free Variable Importance Testing with Machine Learning Methods

報(bào)告人：郭旭教授

摘要：In this paper, we investigate variable importance testing problem in a model-free framework. Some remarkable procedures are developed recently. Despite their success, existing procedures suffer from a significant limitation, that is, they generally require larger training sample and do not have the fastest possible convergence rate under alternative hypothesis. In this paper, we propose a new procedure to test variable importance. Flexible machine learning methods are adopted to estimate unknown functions. Under null hypothesis, our proposed test statistic converges to standard chi-squared distribution. While under local alternative hypotheses, it converges to non-central chi-square distribution. It has non-trivial power against the local alternative hypothesis which converges to the null at the fastest possible rate. We also extend our procedure to test conditional independence. Asymptotic properties are also developed. Numerical studies and two real data examples are conducted to illustrate the performance of our proposed test statistic.

報(bào)告人簡(jiǎn)介：郭旭博士，現(xiàn)為北京師范大學(xué)統(tǒng)計(jì)學(xué)院教授，博士生導(dǎo)師。郭老師一直從事回歸分析中復(fù)雜假設(shè)檢驗(yàn)的理論方法及應(yīng)用研究，近年來旨在對(duì)高維數(shù)據(jù)發(fā)展適當(dāng)有效的檢驗(yàn)方法。部分成果發(fā)表在JRSSB，JASA，Biometrika和JOE?，F(xiàn)主持國(guó)家自然科學(xué)基金優(yōu)秀青年基金。曾榮獲北師大第十一屆“最受本科生歡迎的十佳教師”，北師大第十八屆青教賽一等獎(jiǎng)和北京市第十三屆青教賽三等獎(jiǎng)。

報(bào)告5：Corrected kernel principal component analysis for model structural change detection

報(bào)告人：朱學(xué)虎教授

摘要：This paper develops a method to detect model structural changes by applying a Corrected Kernel Principal Component Analysis (CKPCA) to construct the so-called central distribution deviation subspaces. This approach can efficiently identify the distribution changes in these dimension reduction subspaces. We derive that the locations and number changes in the dimension reduction data subspaces are identical to those in the original data spaces. Meanwhile, we also explain the necessity of using CKPCA as the classical KPCA fails to identify the central distribution deviation subspaces in these problems. Additionally, we extend this approach to clustering by embedding the original data with nonlinear lower dimensional spaces, providing enhanced capabilities for clustering analysis. The numerical studies on synthetic and real data sets suggest that the dimension reduction versions of existing methods for change point detection and clustering significantly improve the performances of existing approaches in finite sample scenarios.

報(bào)告人簡(jiǎn)介：朱學(xué)虎，博士，西安交通大學(xué)教授，博士生導(dǎo)師。目前主要從事統(tǒng)計(jì)學(xué)習(xí)、高維數(shù)據(jù)分析、隱私保護(hù)等領(lǐng)域的基礎(chǔ)理論與應(yīng)用研究。在國(guó)際權(quán)威期刊JASA、JBES、IEEE TGRS以及計(jì)算機(jī)頂會(huì)NeurIPS等發(fā)表論文30余篇，先后主持國(guó)家自然科學(xué)基金面上項(xiàng)目和青年項(xiàng)目、國(guó)家社會(huì)科學(xué)基金項(xiàng)目等；作為骨干成員參與科技部重點(diǎn)研發(fā)項(xiàng)目、國(guó)家自然科學(xué)基金重點(diǎn)項(xiàng)目等；入選2022陜西省高校青年杰出人才支持計(jì)劃、2021年仲英青年學(xué)者等。

甘肅應(yīng)用數(shù)學(xué)中心

甘肅省高校應(yīng)用數(shù)學(xué)與復(fù)雜系統(tǒng)省級(jí)重點(diǎn)實(shí)驗(yàn)室

yl7703永利官網(wǎng)

萃英學(xué)院

2024年8月16日