為更好地推動(dòng)統(tǒng)計(jì)學(xué)、數(shù)據(jù)科學(xué)及相關(guān)學(xué)科的發(fā)展，促進(jìn)國(guó)內(nèi)青年統(tǒng)計(jì)學(xué)者之間的學(xué)術(shù)交流與合作，全國(guó)工業(yè)統(tǒng)計(jì)學(xué)教學(xué)研究會(huì)青年統(tǒng)計(jì)學(xué)家協(xié)會(huì)2026年年會(huì)將于2026年4月11日在西南財(cái)經(jīng)大學(xué)柳林校區(qū)（成都）舉辦。此次會(huì)議由全國(guó)工業(yè)統(tǒng)計(jì)學(xué)教學(xué)研究會(huì)青年統(tǒng)計(jì)學(xué)家協(xié)會(huì)主辦，西南財(cái)經(jīng)大學(xué)統(tǒng)計(jì)與數(shù)據(jù)科學(xué)學(xué)院、西南財(cái)經(jīng)大學(xué)統(tǒng)計(jì)交叉創(chuàng)新研究院、西南財(cái)經(jīng)大學(xué)數(shù)據(jù)科學(xué)與商業(yè)智能聯(lián)合實(shí)驗(yàn)室承辦，《統(tǒng)計(jì)理論及其應(yīng)用（英文）》編輯部、狗熊會(huì)協(xié)辦。論壇邀請(qǐng)國(guó)內(nèi)外知名統(tǒng)計(jì)學(xué)家和杰出青年統(tǒng)計(jì)學(xué)者做大會(huì)報(bào)告，并邀請(qǐng)國(guó)內(nèi)優(yōu)秀青年統(tǒng)計(jì)學(xué)者到會(huì)開(kāi)展深入探討，也為有志于進(jìn)入高校發(fā)展的統(tǒng)計(jì)學(xué)人才以及有意求賢的高校，提供互相展示、溝通和了解的交流平臺(tái)（點(diǎn)擊閱讀原文下載會(huì)議通知）。
大會(huì)報(bào)告
報(bào)告人簡(jiǎn)介
寇綱 教授
寇綱現(xiàn)任全國(guó)政協(xié)委員、湘江實(shí)驗(yàn)室副主任，西南財(cái)經(jīng)大學(xué)大數(shù)據(jù)研究院院長(zhǎng)、中國(guó)系統(tǒng)工程學(xué)會(huì)副理事長(zhǎng)、長(zhǎng)江學(xué)者特聘教授、國(guó)家杰出青年科學(xué)基金獲得者、國(guó)務(wù)院享受政府特殊津貼專(zhuān)家。主持社科重大等多項(xiàng)科研課題；在Science，Nature子刊，UTD24期刊（ISR, JOC）和ICML、AAAI、KDD等頂會(huì)發(fā)表200余篇論文，H指數(shù)77，論文被他人引用2萬(wàn)余次。以第一完成人身份獲教育部高等學(xué)?？茖W(xué)研究?jī)?yōu)秀成果獎(jiǎng)自然科學(xué)一等獎(jiǎng)、人文社會(huì)科學(xué)一等獎(jiǎng)等多項(xiàng)省部級(jí)科研獎(jiǎng)勵(lì)，所撰寫(xiě)的10余份政策建議曾獲得習(xí)近平總書(shū)記等中央領(lǐng)導(dǎo)人批示。
報(bào)告題目
Recommendation Systems Leveraging Multi-view Graph Contrastive Learning and Online Distillation
報(bào)告摘要
Recommendation systems have become deeply embedded in people's daily lives, and users' heavy reliance on them poses non-negligible potential risks to mental health. Furthermore, in healthcare applications, recommendation technology has been successfully deployed across multiple domains including disease prediction, prevention, and medical diagnosis, demonstrating significant value. Typically, recommendation systems leverage rich historical interaction data between users and items to achieve accurate recommendations. However, in practical applications, new users or items often face the cold-start problem due to lack of interaction data. Simultaneously, insufficient interaction information leads to data sparsity issues. These two challenges severely constrain the performance of recommendation systems. To address these limitations, this study first proposes a multi-view graph contrastive learning approach that jointly models attributes and structure. Through an adaptive contrastive learning module, our method dynamically regulates the mutual information levels between the final contrastive views, thereby fully exploiting the rich information contained in both attribute and structural views. For the data sparsity problem, we propose a multi-view fusion recommendation framework. This framework utilizes multi-view graph contrastive learning to integrate user social relationships and item semantic associations, effectively mitigating the negative impact of data scarcity. For cold-start scenarios, we design a bidirectional online distillation mechanism. This enables two-way knowledge transfer between the content-enhanced collaborative embedding network and the content-based embedding network, achieving adaptive fusion of content information and collaborative signals. This approach effectively resolves the cold-start problem while enhancing recommendation performance.
報(bào)告人簡(jiǎn)介
常晉源 教授
常晉源，西南財(cái)經(jīng)大學(xué)光華首席教授、中國(guó)科學(xué)院數(shù)學(xué)與系統(tǒng)科學(xué)研究院研究員，主要從事大規(guī)模復(fù)雜數(shù)據(jù)分析相關(guān)的研究，先后擔(dān)任統(tǒng)計(jì)學(xué)、計(jì)量經(jīng)濟(jì)學(xué)和運(yùn)籌管理國(guó)際頂級(jí)學(xué)術(shù)期刊Journal of the Royal Statistical Society Series B、Journal of Business & Economic Statistics、Journal of the American Statistical Association和Operations Research的副主編，獲得過(guò)國(guó)務(wù)院政府特殊津貼、霍英東教育基金會(huì)高等院校青年教師獎(jiǎng)一等獎(jiǎng)和青年科學(xué)獎(jiǎng)一等獎(jiǎng)、教育部高等學(xué)校科學(xué)研究?jī)?yōu)秀成果獎(jiǎng)、四川省青年科技獎(jiǎng)等多項(xiàng)獎(jiǎng)勵(lì)。
報(bào)告題目
CP-factorization for high dimensional tensor time series and double projection iterations
報(bào)告摘要
We adopt the canonical polyadic (CP) decomposition to model high-dimensional tensor time series. Our primary goal is to identify and estimate the factor loadings in the CP decomposition. We propose a one-pass estimation procedure through standard eigen-analysis for a matrix constructed based on the serial dependence structure of the data. The asymptotic properties of the proposed estimator are established under a general setting as long as the factor loading vectors are algebraically linear independent, allowing the factors to be correlated and the factor loading vectors to be not nearly orthogonal. The procedure adapts to the sparsity of the factor loading vectors, accommodates weak factors, and demonstrates strong performance across a wide range of scenarios. A tractable limiting representation of the estimator is derived, which plays a key role in the related inference problems. To further reduce estimation errors, we also introduce an iterative algorithm based on a novel double projection approach. We theoretically justify the improved convergence rate of the iterative estimator, and also provide the associated limiting distribution. All results are validated through extensive simulations and a real data application.
報(bào)告人簡(jiǎn)介
周帆 副教授
周帆，上海財(cái)經(jīng)大學(xué)統(tǒng)計(jì)與數(shù)據(jù)科學(xué)學(xué)院副教授，教育部青年長(zhǎng)江學(xué)者，博士畢業(yè)于美國(guó)北卡羅來(lái)納大學(xué)教堂山分校，現(xiàn)擔(dān)任統(tǒng)計(jì)學(xué)頂刊JASA的編委。研究興趣包括深度學(xué)習(xí)，強(qiáng)化學(xué)習(xí)的算法與理論，大模型，因果推斷，在包括JASA, JMLR, NeurIPS, ICML, ICLR等統(tǒng)計(jì)學(xué)，機(jī)器學(xué)習(xí)頂刊和頂會(huì)上發(fā)表一作通訊文章數(shù)十篇，曾獲泛華統(tǒng)計(jì)協(xié)會(huì)國(guó)際會(huì)議新研究者獎(jiǎng),UNC James E. Grizzle Distinguished Alumnus Award和Barry H. Margolin Award.
報(bào)告題目
AI for Statistics的一些最新進(jìn)展
報(bào)告摘要
本報(bào)告將介紹我們近期在A(yíng)I for Statistics方面的一系列探索與進(jìn)展。圍繞“大模型的統(tǒng)計(jì)推理能力”這一核心問(wèn)題，我們從底層數(shù)據(jù)、知識(shí)建模與輔助研究三個(gè)層面展開(kāi)研究。首先，我們構(gòu)建了StatEval——首個(gè)面向統(tǒng)計(jì)學(xué)的綜合性問(wèn)答與推理的綜合性數(shù)據(jù)集和評(píng)測(cè)基準(zhǔn)，系統(tǒng)覆蓋從本科與研究生基礎(chǔ)知識(shí)到前沿科研級(jí)證明問(wèn)題，填補(bǔ)了現(xiàn)有大模型基礎(chǔ)數(shù)據(jù)與評(píng)測(cè)中統(tǒng)計(jì)學(xué)維度長(zhǎng)期缺失的空白。其次，基于StatEval，我們進(jìn)一步構(gòu)建了一個(gè)由 基礎(chǔ)知識(shí)、理論定理與研究論文三個(gè)層次組成的統(tǒng)計(jì)知識(shí)圖譜與知識(shí)庫(kù)，可與 RAG 框架結(jié)合，顯著提升基線(xiàn)模型在統(tǒng)計(jì)推理與定理理解方面的能力。在此基礎(chǔ)上，我們還開(kāi)發(fā)了一個(gè)面向統(tǒng)計(jì)研究的AI助手，能夠輔助研究者查找相關(guān)文獻(xiàn)與定理、核查證明思路，并在一定范圍內(nèi)參與簡(jiǎn)單定理的構(gòu)造與證明。
報(bào)告人簡(jiǎn)介
蘭偉 教授
蘭偉，博士畢業(yè)于北京大學(xué)光華管理學(xué)院，現(xiàn)為西南財(cái)經(jīng)大學(xué)教授，博士生導(dǎo)師，統(tǒng)計(jì)與數(shù)據(jù)科學(xué)學(xué)院副院長(zhǎng)，財(cái)經(jīng)數(shù)智科學(xué)創(chuàng)新實(shí)驗(yàn)室主任。主要研究方向?yàn)榇笮途W(wǎng)絡(luò)數(shù)據(jù)分析、實(shí)證資產(chǎn)定價(jià)和投資組合優(yōu)化。主持自科青年科學(xué)基金項(xiàng)目（B類(lèi)）、面上項(xiàng)目和多個(gè)重點(diǎn)項(xiàng)目子課題。在Journal of the American Statistical Association, Annals of Statistics, Journal of Econometrics, Journal of Business & Economic Statistics，經(jīng)濟(jì)學(xué)季刊等國(guó)內(nèi)外知名期刊發(fā)表論文60余篇。
報(bào)告題目
Quantile Social Autoregressive Model
報(bào)告摘要
Research on peer effects typically adopts linear-in-means (LIM) models. These models average responses across peers and therefore cannot capture scenarios where influence comes from better or worse peers. To address this limitation, this paper introduces a quantile social norm defined on the empirical distribution of peers’ responses and develops a novel quantile social autoregressive model. In our setting, the social norm is a peer-group quantile, which allows the data to determine which segment of peers drives individual behavior. To estimate the model, we introduce a new set of moment conditions and instruments constructed from pseudo responses. A kernel-smoothed method is further adopted to obtain the generalized method of moments (GMM)-type estimator. We systematically discuss the existence and uniqueness of equilibrium and the identification conditions. We further establish the consistency and asymptotic normality of the estimator. Monte Carlo experiments and an empirical application show gains in fit and clearer interpretation relative to linear-in-means models.
邀請(qǐng)報(bào)告
本次會(huì)議設(shè)置了20余個(gè)平行分會(huì)場(chǎng)，邀請(qǐng)國(guó)內(nèi)外優(yōu)秀青年學(xué)者近100余人.邀請(qǐng)報(bào)告的主題包括深度學(xué)習(xí)進(jìn)展、高維統(tǒng)計(jì)推斷、生物統(tǒng)計(jì)進(jìn)展、復(fù)雜時(shí)間序列分析、生成模型理論與應(yīng)用、數(shù)據(jù)驅(qū)動(dòng)決策、網(wǎng)絡(luò)結(jié)構(gòu)數(shù)據(jù)分析、教學(xué)獲獎(jiǎng)分享、學(xué)科建設(shè)經(jīng)驗(yàn)、AI在教學(xué)中的應(yīng)用等。
博士生論壇
此次會(huì)議設(shè)有超過(guò)10場(chǎng)博士生論壇，歡迎在讀博士生投稿（投稿要求會(huì)在稍后專(zhuān)門(mén)發(fā)布推文）。一旦入選將有機(jī)會(huì)在博士生論壇進(jìn)行宣講，并且得到travel award。成功宣講的博士生會(huì)得到協(xié)會(huì)頒發(fā)的宣講證書(shū)。
高校招聘專(zhuān)場(chǎng)
為了更好地促進(jìn)高校與博士生之間的交流，協(xié)會(huì)特設(shè)高校招聘專(zhuān)場(chǎng)，費(fèi)用6000元/個(gè)。2024年和2025年的年會(huì)成功吸引了超過(guò)30家高校和企業(yè)到現(xiàn)場(chǎng)進(jìn)行招募。有意向的高校請(qǐng)將基本情況發(fā)送郵件到 [email protected]，與李老師聯(lián)絡(luò)。請(qǐng)?jiān)卩]件中說(shuō)明學(xué)校或?qū)W院的基本情況，聯(lián)系人方式等。
會(huì)議舉辦地點(diǎn)
西南財(cái)經(jīng)大學(xué)柳林校區(qū) 四川成都溫江柳臺(tái)大道555號(hào)
聯(lián)系人：潘蕊 [email protected]
掃描下方二維碼即可報(bào)名參會(huì)（本次會(huì)議不收取會(huì)務(wù)費(fèi)，食宿等費(fèi)用自理）
