Xin Guo

Minheng Chen, Yang-chih Fu, Xin Guo, and Qiang Fu, Social Isolation by Design: Bias in Measuring Core Networks in Taiwan? Social Networks Volume 85, Pages 1-12, May 2026. [post-print: link], [cite]

@article{ChenFuGuoFu2026-officialSite,
  title = {Social isolation by design: {Bias} in measuring core networks in {Taiwan}?},
  journal = {Social Networks},
  volume = {85},
  pages = {1-12},
  year = {2026},
  issn = {0378-8733},
  doi = {https://doi.org/10.1016/j.socnet.2025.11.001},
  url = {https://www.sciencedirect.com/science/article/pii/S037887332500070X},
  author = {Minheng Chen and Yang-chih Fu and Xin Guo and Qiang Fu},
  keywords = {Name generator, Core discussion network, Social desirability bias, Modified Poisson regression, Design errors},
  abstract = {The estimation and measurement of the size of egocentric networks have sparked vigorous discussion and debate. Drawing on datasets from the Taiwan Social Change Survey, this study explores methodological issues pertaining to the change of core networks in Taiwan from 1997 to 2017 via a modified Poisson mixture approach, assesses the efficiency of name generators as a survey instrument via Fisher Information Maximizer, and investigates the role of social desirability in reporting core networks. Net of other effects, the study finds that individuals expressing a strong sense of social desirability report significantly fewer close contacts and face a higher risk of social isolation. Name generators in this study are associated with trivial design errors and can yield estimates comparable to those produced by exact enumeration. These findings are situated in the drastic changes in face-to-face survey interviews as well as the cultural context of Taiwan and, more broadly, East Asia. They call for further research inquiries into methodological issues regarding measuring and estimating egocentric networks in a transnational and modern setting.}
}

Yao Wang, Xin Guo, and Shao-Bo Lin, Kernel-based L2-boosting with structure constraints, Journal of Machine Learning Research, accepted, 2025. [cite]

BibTex Under Construction

Jiaxin Gu, Minheng Chen, Yue Yuan, Xin Guo, Tian-Yi Zhou, and Qiang Fu, Drink like a Man? Modified Poisson Analysis of Adolescent Binge Drinking in the US, 1976-2022, Social Science & Medicine, Volume 364(117553), pages 1-9, January 2025. [post-print: link1,link2], [cite]

@article{Gu-Chen-Yuan-Guo-Zhou-Fu-2025Drink,
  title={Drink like a man? Modified {Poisson} analysis of adolescent binge drinking in the US, 1976--2022},
  author={Gu, Jiaxin and Chen, Minheng and Yuan, Yue and Guo, Xin and Zhou, Tian-Yi and Fu, Qiang},
  journal={Social Science \& Medicine},
  volume={364},
  number={117553},
  pages={1-9},
  year={2025},
  publisher={Elsevier}
}

Xin Guo and Qiang Fu, The design and optimality of survey counts: a unified framework via the Fisher Information Maximizer, Sociological Methods and Research, 53(3):1319-1349, August 2024. [post-print: link1,link2,link3], [cite]

@Article{Guo-Fu-2024FIM-OfficialSite,
  author   = {Guo, Xin and Fu, Qiang},
  journal  = {Sociological Methods \& Research},
  title    = {The design and optimality of survey counts: a unified framework via the {Fisher Information Maximizer}},
  year     = {2022},
  number   = {0},
  pages    = {00491241221113877},
  volume   = {0},
  abstract = {Grouped and right-censored (GRC) counts have been used in a wide range of attitudinal and behavioural surveys yet they cannot be readily analyzed or assessed by conventional statistical models. This study develops a unified regression framework for the design and optimality of GRC counts in surveys. To process infinitely many grouping schemes for the optimum design, we propose a new two-stage algorithm, the Fisher Information Maximizer (FIM), which utilizes estimates from generalized linear models to find a global optimal grouping scheme among all possible N-group schemes. After we define, decompose, and calculate different types of regressor-specific design errors, our analyses from both simulation and empirical examples suggest that: 1) the optimum design of GRC counts is able to reduce the grouping error to zero, 2) the performance of modified Poisson estimators using GRC counts can be comparable to that of Poisson regression, and 3) the optimum design is usually able to achieve the same estimation efficiency with a smaller sample size.},
  doi      = {10.1177/00491241221113877},
  eprint   = {https://doi.org/10.1177/00491241221113877},
  url      = {https://doi.org/10.1177/00491241221113877},
}

Jacob Westerhout, Trung Tin Nguyen, Xin Guo, and Hien Duy Nguyen, On the asymptotic distribution of the minimum empirical risk, ICML 2024 | The Forty-first International Conference on Machine Learning, Vienna, Austria, 2024. [post-print: link1,link2], [cite]

@InProceedings{Westerhout-Nguyen-Guo-Nguyen-2024ICML,
  title = 	 {On the Asymptotic Distribution of the Minimum Empirical Risk},
  author =       {Westerhout, Jacob and Nguyen, Trungtin and Guo, Xin and Nguyen, Hien Duy},
  booktitle = 	 {Proceedings of the 41st International Conference on Machine Learning},
  pages = 	 {52869--52902},
  year = 	 {2024},
  editor = 	 {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix},
  volume = 	 {235},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {21--27 Jul},
  publisher =    {PMLR},
  pdf = 	 {https://raw.githubusercontent.com/mlresearch/v235/main/assets/westerhout24a/westerhout24a.pdf},
  url = 	 {https://proceedings.mlr.press/v235/westerhout24a.html},
  abstract = 	 {Empirical risk minimization (ERM) is a foundational framework for the estimation of solutions to statistical and machine learning problems. Characterizing the distributional properties of the minimum empirical risk (MER) provides valuable tools for conducting inference and assessing the goodness of model fit. We provide a comprehensive account of the asymptotic distribution for the order-$\sqrt{n}$ blowup of the MER under generic and abstract assumptions, and present practical conditions under which our theorems hold. Our results improve upon and relax the assumptions made in previous works. Specifically, we provide asymptotic distributions for MERs for non-independent and identically distributed data, and when the loss functions may be discontinuous or indexed by non-Euclidean spaces. We further present results that enable the application of these asymptotics for statistical inference. Specifically, the construction of consistent confidence sets using the bootstrap and consistent hypothesis tests using penalized model selection. We illustrate the utility of our approach by applying our results to neural network problems.}
}

Chendi Wang, Xin Guo, and Qiang Wu, Learning with Centered Reproducing Kernels, Analysis and Applications, 22(03):507-534, 2024. [post-print: link1,link2], [cite]

@Article{Wang-Guo-Wu-2024Centered-MR4734646,
  author   = {Wang, Chendi and Guo, Xin and Wu, Qiang},
  journal  = {Anal. Appl. (Singap.)},
  title    = {Learning with centered reproducing kernels},
  year     = {2024},
  issn     = {0219-5305,1793-6861},
  number   = {3},
  pages    = {507--534},
  volume   = {22},
  doi      = {10.1142/S0219530523400018},
  fjournal = {Analysis and Applications},
  mrclass  = {46N30 (46E22 62G08)},
  mrnumber = {4734646},
  url      = {https://doi.org/10.1142/S0219530523400018},
}

Jiaxin Gu, Xin Guo, Xiaoxi Liu, Yue Yuan, Yushu Zhu, Minheng Chen, Tian-Yi Zhou, and Qiang Fu, Gone with the weed: incidents of adolescent marijuana use in the United States, 1976-2021, Annals of Epidemiology, Volume 88, Pages 23-29, December 2023. [post-print: link1,link2], [cite]

@Article{Gu-Guo-Liu-Yuan-Zhu-Chen-Zhou-Fu-2023Gone-officialSite,
  author   = {Gu, Jiaxin and Guo, Xin and Liu, Xiaoxi and Yuan, Yue and Zhu, Yushu and Chen, Minheng and Zhou, Tian-Yi and Fu, Qiang},
  title    = {Gone with the weed: incidents of adolescent marijuana use in the {United States}, 1976–2021},
  journal  = {Annals of Epidemiology},
  year     = {2023},
  volume   = {88},
  pages    = {23-29},
  issn     = {1047-2797},
  abstract = {ABSTRACT
Purpose
This study sought to examine grouped and right-censored (GRC) counts of adolescent marijuana use and estimate its temporal trajectories and sociodemographic disparities over almost half a century.
Methods
After compiling 46 waves of nationally representative data from the Monitoring the Future (MTF) study from 1976 to 2021 (sample size = 491,348), we utilized an innovative modified Poisson (mixture) approach to analyze past-year marijuana use quantified by GRC counts.
Results
The overall reduction in incidence rates of marijuana use was attributable to an almost 40\% reduction in the risk of marijuana use (with the proportion of at-risk adolescents at 51.36\% in 1979 and 31.53\% in 2021). Despite substantial changes over the study period, the recent incidence rates for at-risk individuals were similar to those in the early 1980s. Living in an intact family was a protective factor against adolescent marijuana use over time.
Conclusions
The incidence rates of marijuana use among at-risk students, especially those from disadvantaged families, remained high over the study period. The modified Poisson (mixture) approach serves as the preferred tool for modeling GRC responses. It is essential to distinguish among risk, at-risk incidence, and overall incidence when assessing substance use and other risky behaviors.},
  doi      = {https://doi.org/10.1016/j.annepidem.2023.10.002},
  keywords = {Marijuana, Modified Poisson regression, Adolescent, Incidence, Grouped and right-censored count},
  url      = {https://www.sciencedirect.com/science/article/pii/S1047279723001916},
}
}

Xin Guo, Zheng-Chu Guo, and Lei Shi, Capacity dependent analysis for functional online learning algorithms, Applied and Computational Harmonic Analysis, Volume 67(101567):1-30, November 2023. [post-print: link1,link2], [cite]

@article {GuoGuoShi2023-MR4612182,
    AUTHOR = {Guo, Xin and Guo, Zheng-Chu and Shi, Lei},
     TITLE = {Capacity dependent analysis for functional online learning
              algorithms},
   JOURNAL = {Appl. Comput. Harmon. Anal.},
  FJOURNAL = {Applied and Computational Harmonic Analysis. Time-Frequency
              and Time-Scale Analysis, Wavelets, Numerical Algorithms, and
              Applications},
    VOLUME = {67},
      YEAR = {2023},
     PAGES = {Paper No. 101567, 30},
      ISSN = {1063-5203,1096-603X},
   MRCLASS = {65K10 (62R10 68T05)},
  MRNUMBER = {4612182},
       DOI = {10.1016/j.acha.2023.06.002},
       URL = {https://doi.org/10.1016/j.acha.2023.06.002},
}

Xin Guo, Junhong Lin, and Ding-Xuan Zhou, Rates of convergence of randomized Kaczmarz algorithms in Hilbert spaces, Applied and Computational Harmonic Analysis, 61:288-318, November 2022. [post-print: link1,link2], [cite]

@article {GuoLinZhou2022-MR4466675,
    AUTHOR = {Guo, Xin and Lin, Junhong and Zhou, Ding-Xuan},
     TITLE = {Rates of convergence of randomized {K}aczmarz algorithms in
              {H}ilbert spaces},
   JOURNAL = {Appl. Comput. Harmon. Anal.},
  FJOURNAL = {Applied and Computational Harmonic Analysis. Time-Frequency
              and Time-Scale Analysis, Wavelets, Numerical Algorithms, and
              Applications},
    VOLUME = {61},
      YEAR = {2022},
     PAGES = {288--318},
      ISSN = {1063-5203,1096-603X},
   MRCLASS = {41A25 (41A65 46N10 65J05)},
  MRNUMBER = {4466675},
MRREVIEWER = {Danilo\ Costarelli},
       DOI = {10.1016/j.acha.2022.07.005},
       URL = {https://doi.org/10.1016/j.acha.2022.07.005},
}

Qiang Fu, Yufan Zhuang, Yushu Zhu, and Xin Guo, Sleeping lion or sick man? Machine learning approaches to deciphering heterogeneous images of Chinese in North America, Annals of the American Association of Geographers, 112(7):2045-2063, 2022. [post-print: link1,link2,link3,link4], [cite]

@Article{FuEtAlAAG2022-OfficialSite,
  author    = {Fu, Qiang and Zhuang, Yufan and Zhu, Yushu and Guo, Xin},
  journal   = {Annals of the American Association of Geographers},
  title     = {Sleeping lion or sick man? Machine learning approaches to deciphering heterogeneous images of {Chinese} in {North} {America}},
  year      = {2022},
  number    = {7},
  pages     = {2045--2063},
  volume    = {112},
  doi       = {10.1080/24694452.2022.2042180},
  publisher = {Taylor \& Francis},
}

Xiaming Chen, Bohao Tang, Jun Fan, and Xin Guo, Online gradient descent algorithms for functional data learning, Journal of Complexity, 70(101635):1-14, June 2022. [post-print: link1,link2,link3], [cite]

@Article{ChenTangFanGuoComplexity2022-MR4388513,
  author   = {Chen, Xiaming and Tang, Bohao and Fan, Jun and Guo, Xin},
  journal  = {J. Complexity},
  title    = {Online gradient descent algorithms for functional data learning},
  year     = {2022},
  issn     = {0885-064X},
  pages    = {Paper No. 101635, 14},
  volume   = {70},
  abstract = {Functional linear model is a fruitfully applied general framework for regression problems, including those with intrinsically infinite-dimensional data. Online gradient descent methods, despite their evidenced power of processing online or large-sized data, are not well studied for learning with functional data. In this paper, we study reproducing kernel-based online learning algorithms for functional data, and derive convergence rates for the expected excess prediction risk under both online and finite-horizon settings of step-sizes respectively. It is well understood that nontrivial uniform convergence rates for the estimation task depend on the regularity of the slope function. Surprisingly, the convergence rates we derive for the prediction task can assume no regularity from slope. Our analysis reveals the intrinsic difference between the estimation task and the prediction task in functional data learning.},
  doi      = {10.1016/j.jco.2021.101635},
  fjournal = {Journal of Complexity},
  keywords = {Learning theory, online learning, gradient descent, reproducing kernel Hilbert space, error analysis},
  mrclass  = {62R10 (46N30 68T05)},
  mrnumber = {4388513},
  url      = {https://doi.org/10.1016/j.jco.2021.101635},
}

Yue Yuan, Jiaxin Gu, Xin Guo, Yushu Zhu, and Qiang Fu, Detecting temporal anomalies with pseudo age groups: homeownership in Canada, 1981 to 2016, Population, Space and Place, 28(1,e2532):1-18, January 2022. [post-print: link1,link2,link3], [cite]

@Article{YuanEtAl2021-HomePage,
  author   = {Yuan, Yue and Gu, Jiaxin and Guo, Xin and Zhu, Yushu and Fu, Qiang},
  journal  = {Population, Space and Place},
  title    = {Detecting temporal anomalies with pseudo age groups: homeownership in {Canada}, 1981 to 2016},
  year     = {2022},
  number   = {e2532},
  pages    = {1-18},
  volume   = {28},
  doi      = {https://doi.org/10.1002/psp.2532},
  keywords = {age-period-cohort analysis, homeownership, multiple imputation, pseudo data, structural change analysis},
}

Qiang Fu, Tian-Yi Zhou, and Xin Guo, Modified Poisson regression analysis of grouped and right-censored counts, [R package: GRCRegression], Journal of the Royal Statistical Society, Series A, 184(4):1347-1367, October 2021. [post-print: link1,link2], [cite]

@Article{FuZhouGuoJRSSA2021-MR4344640,
  author   = {Fu, Qiang and Zhou, Tian-Yi and Guo, Xin},
  journal  = {J. Roy. Statist. Soc. Ser. A},
  title    = {Modified {P}oisson regression analysis of grouped and right-censored counts},
  year     = {2021},
  issn     = {0964-1998},
  number   = {4},
  pages    = {1347--1367},
  volume   = {184},
  abstract = {Abstract Grouped and right-censored (GRC) counts are widely used in criminology, demography, epidemiology, marketing, sociology, psychology and other related disciplines to study behavioural and event frequencies, especially when sensitive research topics or individuals with possibly lower cognitive capacities are at stake. Yet, the co-existence of grouping and right-censoring poses major difficulties in regression analysis. To implement generalised linear regression of GRC counts, we derive modified Poisson estimators and their asymptotic properties, develop a hybrid line search algorithm for parameter inference, demonstrate the finite-sample performance of these estimators via simulation, and evaluate its empirical applicability based on survey data of drug use in America. This method has a clear methodological advantage over the ordered logistic model for analysing GRC counts.},
  doi      = {10.1111/rssa.12678},
  eprint   = {https://rss.onlinelibrary.wiley.com/doi/pdf/10.1111/rssa.12678},
  fjournal = {Journal of the Royal Statistical Society. Series A. Statistics in Society},
  keywords = {fisher information, grouped and right-censored counts, hybrid line search, modified Poisson estimators, regression analysis, zero inflation},
  mrclass  = {Expansion},
  mrnumber = {4344640},
  url      = {https://doi.org/10.1111/rssa.12678},
}

Jiaxin Gu, Xin Guo, Gerry Veenstra, Yushu Zhu, and Qiang Fu, Adolescent marijuana use in the United States and structural breaks: an age-period-cohort analysis, 1991--2018, American Journal of Epidemiology, 190(6):1056-1063, June 2021. [post-print: link1,link2], [cite]

@Article{GuGuoVeenstraZhuFu2020AJE-AJEHomepage,
  author   = {Gu, Jiaxin and Guo, Xin and Veenstra, Gerry and Zhu, Yushu and Fu, Qiang},
  journal  = {American Journal of Epidemiology},
  title    = {Adolescent marijuana use in the {United States} and structural breaks: an age-period-cohort analysis, 1991--2018},
  year     = {2020},
  issn     = {0002-9262},
  month    = {12},
  number   = {6},
  pages    = {1056--1063},
  volume   = {190},
  abstract = {{To investigate temporal patterns, sociodemographic gradients, and structural breaks in adolescent marijuana use in the United States from 1991 to 2018, we used hierarchical age-period-cohort logistic regression models to distinguish temporal effects of marijuana use among 8th, 10th, and 12th graders from 28 waves of the Monitoring the Future survey (1991-2018). Structural breaks in period effects were further detected via a dynamic-programing-based method. Net of other effects, we found a clear age-related increase in the probability of marijuana use (10.46\\%, 23.17\\%, and 31.19\\% for 8th, 10th, and 12th graders, respectively). Period effects showed a substantial increase over time (from 16.23\\% in 2006 to 26.38\\% in 2018), while cohort effects remained stable throughout the study period. Risk of adolescent marijuana use varied by sex, racial group, family status, and parental education. Significant structural breaks during 1995-1996, 2006-2008, and 2011-2013 were identified in different subpopulations. A steady increase in marijuana use among adolescents during the latter years of this time period was identified. Adolescents who were male, were non-Black, lived in nonintact families, and had less educated parents were especially at risk of marijuana usage. Trends in adolescent marijuana use changed significantly during times of economic crisis.}},
  doi      = {10.1093/aje/kwaa269},
  eprint   = {https://academic.oup.com/aje/article-pdf/190/6/1056/38391500/kwaa269.pdf},
  url      = {https://doi.org/10.1093/aje/kwaa269},
}

Qiang Fu, Xin Guo, Sun Young Jeon, Eric Reither, Emma Zang, and Kenneth Land, The uses and abuses of an age-period-cohort method: on the linear algebra and statistical properties of intrinsic and related estimators, Mathematical Foundations of Computing, 4(1):45-59, February 2021. [post-print: link1,link2], [cite]

@Article{FuEtAlAbuseMFC2021-OfficialSite,
  author  = {Fu, Qiang and Guo, Xin and Jeon, Sun Young and Reither, Eric N. and Zang, Emma and Land, Kenneth C.},
  journal = {Mathematical Foundations of Computing},
  title   = {The uses and abuses of an age-period-cohort method: on the linear algebra and statistical properties of intrinsic and related estimators},
  year    = {2021},
  number  = {1},
  pages   = {45--59},
  volume  = {4},
}

Qiang Fu, Yufan Zhuang, Jiaxin Gu, Yushu Zhu, and Xin Guo, Agreeing to disagree: choosing among eight topic-modeling methods, Big Data Research, 23(100173):1-9, 15 February 2021. [post-print: link1,link2], [cite]

@Article{FuZhuangGuZhuGuoBDR2021-BDRHomepage,
  author   = {Fu, Qiang and Zhuang, Yufan and Gu, Jiaxin and Zhu, Yushu and Guo, Xin},
  journal  = {Big Data Research},
  title    = {Agreeing to disagree: choosing among eight topic-modeling methods},
  year     = {2021},
  issn     = {2214-5796},
  pages    = {100173},
  volume   = {23},
  abstract = {Topic modeling is a key research area in natural language processing and has inspired innovative studies in a wide array of social-science disciplines. Yet, the use of topic modeling in computational social science has been hampered by two critical issues. First, social scientists tend to focus on a few standard ways of topic modeling. Our understanding of semantic patterns has not been informed by rapid methodological advances in topic modeling. Moreover, a systematic comparison of the performance of different methods in this field is warranted. Second, the choice of the optimal number of topics remains a challenging task. A comparison of topic-modeling techniques has rarely been situated in a social-science context and the choice appears to be arbitrary for most social scientists. Based on about 120,000 Canadian newspaper articles since 1977, we review and compare eight traditional, generative, and neural methods for topic modeling (Latent Semantic Analysis, Principal Component Analysis, Factor Analysis, Non-negative Matrix Factorization, Latent Dirichlet Allocation, Neural Autoregressive Topic Model, Neural Variational Document Model, and Hierarchical Dirichlet Process). Three measures (coherence statistics, held-out likelihood, and graph-based dimensionality selection) are then used to assess the performance of these methods. Findings are presented and discussed to guide the choice of topic-modeling methods, especially in social science research.},
  doi      = {https://doi.org/10.1016/j.bdr.2020.100173},
  keywords = {Topic modeling, Natural language processing, Computational social science, Optimal number of topics},
  url      = {https://www.sciencedirect.com/science/article/pii/S2214579620300411},
}

Xin Guo, Lexin Li, and Qiang Wu, Modeling interactive components by coordinate kernel polynomial models, Mathematical Foundations of Computing, 3(4):263-277, November 2020. [post-print: link1,link2], [cite]

@Article{GuoLiWu2020-MFCOfficialWeb,
  author   = {Guo, Xin and Li, Lexin and Wu, Qiang},
  journal  = {Mathematical Foundations of Computing},
  title    = {Modeling interactive components by coordinate kernel polynomial models},
  year     = {2020},
  issn     = {A0000-0001},
  number   = {A0000-0001_2020_4_263},
  pages    = {263--277},
  volume   = {3},
  abstract = {We proposed the use of coordinate kernel polynomials in kernel regression. This new approach, called coordinate kernel polynomial regression, can simultaneously identify active variables and effective interactive components. Reparametrization refinement is found critical to improve the modeling accuracy and prediction power. The post-training component selection allows one to identify effective interactive components. Generalization error bounds are used to explain the effectiveness of the algorithm from a learning theory perspective and simulation studies are used to show its empirical effectiveness.},
  doi      = {10.3934/mfc.2020010},
  keywords = {Interactive component and kernel method and coordinate kernel polynomial model and reparametrization and generalization and information criterion},
  url      = {http://aimsciences.org/article/doi/10.3934/mfc.2020010},
}

Qiang Fu, Xin Guo, and Kenneth C. Land, Optimizing count responses in surveys: a machine-learning approach, [R package: GRCdata], Sociological Methods and Research, 49(3):637-671, August 2020. [post-print: link1,link2], [cite]

@Article{FuGuoLandSMR2020-SAGEJournalsHomepage,
  author   = {Fu, Qiang and Guo, Xin and Land, Kenneth C.},
  journal  = {Sociological Methods \& Research},
  title    = {Optimizing count responses in surveys: a machine-learning approach},
  year     = {2020},
  number   = {3},
  pages    = {637--671},
  volume   = {49},
  abstract = {Count responses with grouping and right censoring have long been used in surveys to study a variety of behaviors, status, and attitudes. Yet grouping or right-censoring decisions of count responses still rely on arbitrary choices made by researchers. We develop a new method for evaluating grouping and right-censoring decisions of count responses from a (semisupervised) machine-learning perspective. This article uses Poisson multinomial mixture models to conceptualize the data-generating process of count responses with grouping and right censoring and demonstrates the link between grouping-scheme choices and asymptotic distributions of the Poisson mixture. To search for the optimal grouping scheme maximizing objective functions of the Fisher information (matrix), an innovative three-step M algorithm is then proposed to process infinitely many grouping schemes based on Bayesian A-, D-, and E-optimalities. A new R package is developed to implement this algorithm and evaluate grouping schemes of count responses. Results show that an optimal grouping scheme not only leads to a more efficient sampling design but also outperforms a nonoptimal one even if the latter has more groups.},
  doi      = {10.1177/0049124117747302},
  eprint   = {https://doi.org/10.1177/0049124117747302},
  url      = {https://doi.org/10.1177/0049124117747302},
}

Xin Guo, Qiang Fu, Yue Wang, and Kenneth C. Land, A numerical method to compute Fisher information for a special case of heterogeneous negative binomial regression, Communications on Pure and Applied Analysis, 19(8):4179-4189, August 2020. [post-print: link1,link2], [cite]

@Article{GuoFuWangLandCPAA2020-MR4112019,
  author   = {Guo, Xin and Fu, Qiang and Wang, Yue and Land, Kenneth C.},
  journal  = {Commun. Pure Appl. Anal.},
  title    = {A numerical method to compute {F}isher information for a special case of heterogeneous negative binomial regression},
  year     = {2020},
  issn     = {1534-0392},
  number   = {8},
  pages    = {4179--4189},
  volume   = {19},
  doi      = {10.3934/cpaa.2020187},
  fjournal = {Communications on Pure and Applied Analysis},
  mrclass  = {62J12 (94A17)},
  mrnumber = {4112019},
  url      = {https://doi.org/10.3934/cpaa.2020187},
}

Xin Guo, Ting Hu, and Qiang Wu, Distributed minimum error entropy algorithms, Journal of Machine Learning Research, 21(126):1-31, July 2020. [post-print: link1,link2], [cite]

@Article{GuoHuWu2020-MR4138110,
  author   = {Guo, Xin and Hu, Ting and Wu, Qiang},
  journal  = {J. Mach. Learn. Res.},
  title    = {Distributed minimum error entropy algorithms},
  year     = {2020},
  issn     = {1532-4435},
  pages    = {Paper No. 126, 31},
  volume   = {21},
  fjournal = {Journal of Machine Learning Research (JMLR)},
  mrclass  = {62J02 (60E15 62G08 68T05 90C48 90C90 94A17)},
  mrnumber = {4138110},
}

Qiang Fu, Yufan Zhuang, Jiaxin Gu, Yushu Zhu, Huihui Qin, and Xin Guo, Search for K: assessing five topic-modeling approaches to 120,000 Canadian articles, 2019 IEEE International Conference on Big Data (Big Data), Los Angeles, CA, USA, pp. 3640-3647, 2019. [post-print: link1,link2],

Huihui Qin and Xin Guo, Semi-supervised learning with summary statistics, Analysis and Applications, 17(05):837-851, 2019. [post-print: link1,link2], [cite]

@Article{QinGuo2019-MR3998502,
  author   = {Qin, Huihui and Guo, Xin},
  journal  = {Anal. Appl.},
  title    = {Semi-supervised learning with summary statistics},
  year     = {2019},
  issn     = {0219-5305},
  number   = {5},
  pages    = {837--851},
  volume   = {17},
  doi      = {10.1142/S0219530519400037},
  fjournal = {Analysis and Applications},
  mrclass  = {68T05 (62G08 62G20 68P25)},
  mrnumber = {3998502},
  url      = {https://doi.org/10.1142/S0219530519400037},
}

Qiang Fu, Xin Guo, and Kenneth C. Land, A Poisson-multinomial mixture approach to grouped and right-censored counts, Communications in Statistics - Theory and Methods, 47(2):427-447, 2018. [post-print: link1,link2], [cite]

@Article{FuGuoLand2018-MR3765083,
  author   = {Fu, Qiang and Guo, Xin and Land, Kenneth C.},
  journal  = {Comm. Statist. Theory Methods},
  title    = {A {P}oisson-multinomial mixture approach to grouped and right-censored counts},
  year     = {2018},
  issn     = {0361-0926},
  number   = {2},
  pages    = {427--447},
  volume   = {47},
  doi      = {10.1080/03610926.2017.1303736},
  fjournal = {Communications in Statistics. Theory and Methods},
  mrclass  = {62N01 (62G05 62G20 62P10)},
  mrnumber = {3765083},
  url      = {https://doi.org/10.1080/03610926.2017.1303736},
}

Shao-Bo Lin, Xin Guo, and Ding-Xuan Zhou, Distributed learning with regularized least squares, Journal of Machine Learning Research, 18(92):1-31, 2017. [post-print: link1,link2], [cite]

@Article{LinGuoZhou2017-MR3714255,
  author   = {Lin, Shao-Bo and Guo, Xin and Zhou, Ding-Xuan},
  journal  = {J. Mach. Learn. Res.},
  title    = {Distributed learning with regularized least squares},
  year     = {2017},
  issn     = {1532-4435},
  pages    = {Paper No. 92, 31},
  volume   = {18},
  doi      = {10.1016/j.physletb.2016.11.035},
  fjournal = {Journal of Machine Learning Research (JMLR)},
  mrclass  = {68T05 (62G05 62G20 62J07)},
  mrnumber = {3714255},
  url      = {https://doi.org/10.1016/j.physletb.2016.11.035},
}

Zheng-Chu Guo, Dao-Hong Xiang, Xin Guo, and Ding-Xuan Zhou, Thresholded spectral algorithms for sparse approximations, Analysis and Applications, 15(3):433-455, 2017. [post-print: link], [cite]

@Article{GuoXiangGuoZhou2017-MR3636064,
  author   = {Guo, Zheng-Chu and Xiang, Dao-Hong and Guo, Xin and Zhou, Ding-Xuan},
  journal  = {Anal. Appl.},
  title    = {Thresholded spectral algorithms for sparse approximations},
  year     = {2017},
  issn     = {0219-5305},
  number   = {3},
  pages    = {433--455},
  volume   = {15},
  doi      = {10.1142/S0219530517500026},
  fjournal = {Analysis and Applications},
  mrclass  = {62G08 (41A25 65C60 68T05)},
  mrnumber = {3636064},
  url      = {https://doi.org/10.1142/S0219530517500026},
}

Kenneth C. Land, Qiang Fu, Xin Guo, Sun Young Jeon, Eric N. Reither, and Emma Zang, Playing with the rules and making misleading statements: a response to Luo, Hodges, Winship, and Powers, (invited paper), American Journal of Sociology, 122(3):962-973, November 2016. [post-print: link1,link2], [cite]

@Article{LandEtAlPlaying2016-AJSOfficialSite,
  author  = {Land, Kenneth C. and Fu, Qiang and Guo, Xin and Jeon, Sun Y. and Reither, Eric N. and Zang, Emma},
  journal = {American Journal of Sociology},
  title   = {Playing with the rules and making misleading statements: a response to {Luo}, {Hodges}, {Winship}, and {Powers}},
  year    = {2016},
  number  = {3},
  pages   = {962--973},
  volume  = {122},
  doi     = {10.1086/689853},
  eprint  = {https://doi.org/10.1086/689853},
  url     = {https://doi.org/10.1086/689853},
}

Kevin A. McGoff, Xin Guo, Anastasia Deckard, Christina M. Kelliher, Adam R. Leman, Lauren J. Francey, John B. Hogenesch, Steven B. Haase, and John L. Harer, The Local Edge Machine: inference of dynamic models of gene regulation, (software package: Local Edge Machine), Genome Biology, 17:214, 2016. [post-print: link], [cite]

@Article{McGoffEtAl2016LEM,
  author    = {McGoff, Kevin A. and Guo, Xin and Deckard, Anastasia and Kelliher, Christina M. and Leman, Adam R. and Francey, Lauren J. and Hogenesch, John B. and Haase, Steven B. and Harer, John L.},
  journal   = {Genome Biology},
  title     = {The {Local Edge Machine}: inference of dynamic models of gene regulation},
  year      = {2016},
  month     = {Oct},
  number    = {214},
  volume    = {17},
  doi       = {10.1186/s13059-016-1076-z},
  publisher = {Springer Science and Business Media {LLC}},
}

Xin Guo, Jun Fan, and Ding-Xuan Zhou, Sparsity and error analysis of empirical feature-based regularization schemes, Journal of Machine Learning Research, 17(89):1-34, 2016. [post-print: link], [cite]

@Article{GuoFanZhou2016-MR3543495,
  author   = {Guo, Xin and Fan, Jun and Zhou, Ding-Xuan},
  journal  = {J. Mach. Learn. Res.},
  title    = {Sparsity and error analysis of empirical feature-based regularization schemes},
  year     = {2016},
  issn     = {1532-4435},
  pages    = {Paper No. 89, 34},
  volume   = {17},
  fjournal = {Journal of Machine Learning Research (JMLR)},
  mrclass  = {62G08 (62J07 68T05)},
  mrnumber = {3543495},
}

Wen-Jun Shen, Hau-San Wong, Quan-Wu Xiao, Xin Guo, and Stephen Smale, Introduction to the peptide binding problem of computational immunology: new results, Foundations of Computational Mathematics. 14(5):951-984. (The paper was first circulated with the title "Towards a mathematical foundation of immunology and amino acid chains" on arXiv https://arxiv.org/abs/1205.6031v2. All the simulation code is available upon request.) October, 2014. [post-print: link], [cite]

@Article{ShenEtAl2014-MR3260256,
  author   = {Shen, Wen-Jun and Wong, Hau-San and Xiao, Quan-Wu and Guo, Xin and Smale, Stephen},
  journal  = {Found. Comput. Math.},
  title    = {Introduction to the peptide binding problem of computational immunology: new results},
  year     = {2014},
  issn     = {1615-3375},
  number   = {5},
  pages    = {951--984},
  volume   = {14},
  doi      = {10.1007/s10208-013-9173-9},
  fjournal = {Foundations of Computational Mathematics. The Journal of the Society for the Foundations of Computational Mathematics},
  mrclass  = {92C40 (62H30 62P10 92B15)},
  mrnumber = {3260256},
  url      = {https://doi.org/10.1007/s10208-013-9173-9},
}

Wen-Jun Shen, Yu Ting Wei, Xin Guo, Stephen Smale, Hau-San Wong, and Shuai Cheng Li, MHC binding prediction with KernelRLSpan and its variations. Journal of Immunological Methods. 406:10-20, April 2014. [cite]

@Article{ShenEtAlImmuMethods2014-ScienceDirect,
  author   = {Wen-Jun Shen and Yu Ting Wei and Xin Guo and Stephen Smale and Hau-San Wong and Shuai Cheng Li},
  journal  = {Journal of Immunological Methods},
  title    = {{MHC} binding prediction with {KernelRLSpan} and its variations},
  year     = {2014},
  issn     = {0022-1759},
  pages    = {10--20},
  volume   = {406},
  abstract = {Antigenic peptides presented to T cells by MHC molecules are essential for T or B cells to proliferate and eventually differentiate into effector cells or memory cells. MHC binding prediction is an active research area. Reliable predictors are demanded to identify potential vaccine candidates. The recent kernel-based algorithm KernelRLSpan (Shen et al., 2013) shows promising power on MHC II binding prediction. Here, KernelRLSpan is modified and applied to MHC I binding prediction, which we refer to as KernelRLSpanI. Besides this, we develop a novel consensus method to predict naturally processed peptides through integrating KernelRLSpanI with two state-of-the-art predictors NetMHCpan and NetMHC. The consensus method achieved top performance in the Machine Learning in Immunology (MLI) 2012 Competition,33URL: http://bio.dfci.harvard.edu/DFRMLI/HTML/natural.php. group 2. We also introduce our progress of improving our MHC II binding prediction method KernelRLSpan by diffusion map.},
  doi      = {https://doi.org/10.1016/j.jim.2014.02.007},
  keywords = {Major histocompatibility complex class I, Major histocompatibility complex class II, MHC, Peptide binding prediction, String kernel, Eluted peptide prediction, Diffusion map},
  url      = {https://www.sciencedirect.com/science/article/pii/S0022175914000532},
}

Xin Guo and Ding-Xuan Zhou, An empirical feature-based learning algorithm producing sparse approximations, Applied and Computational Harmonic Analysis. 32(3):389-400, 2012. [post-print: link], [cite]

@Article{GuoZhou2012-MR2892740,
  author   = {Guo, Xin and Zhou, Ding-Xuan},
  journal  = {Appl. Comput. Harmon. Anal.},
  title    = {An empirical feature-based learning algorithm producing sparse approximations},
  year     = {2012},
  issn     = {1063-5203},
  number   = {3},
  pages    = {389--400},
  volume   = {32},
  doi      = {10.1016/j.acha.2011.07.005},
  fjournal = {Applied and Computational Harmonic Analysis. Time-Frequency and Time-Scale Analysis, Wavelets, Numerical Algorithms, and Applications},
  mrclass  = {62G08 (62J07)},
  mrnumber = {2892740},
  url      = {https://doi.org/10.1016/j.acha.2011.07.005},
}

Xin Guo, Learning gradients via an early stopping gradient descent method, Journal of Approximation Theory. 162(11):1919-1944, November 2010. [post-print: link], [cite]

@Article{Guo2010-MR2732915,
  author   = {Guo, Xin},
  journal  = {J. Approx. Theory},
  title    = {Learning gradients via an early stopping gradient descent method},
  year     = {2010},
  issn     = {0021-9045},
  number   = {11},
  pages    = {1919--1944},
  volume   = {162},
  doi      = {10.1016/j.jat.2010.05.004},
  fjournal = {Journal of Approximation Theory},
  mrclass  = {41A36 (62G08 68T05)},
  mrnumber = {2732915},
  url      = {https://doi.org/10.1016/j.jat.2010.05.004},
}

Lei Shi, Xin Guo, and Ding-Xuan Zhou, Hermite learning with gradient data. Journal of Computational and Applied Mathematics. 233(11):3046-3059, 1 April 2010. [cite]

@Article{ShiGuoZhou2010-MR2592278,
  author   = {Shi, Lei and Guo, Xin and Zhou, Ding-Xuan},
  journal  = {J. Comput. Appl. Math.},
  title    = {Hermite learning with gradient data},
  year     = {2010},
  issn     = {0377-0427},
  number   = {11},
  pages    = {3046--3059},
  volume   = {233},
  doi      = {10.1016/j.cam.2009.11.059},
  fjournal = {Journal of Computational and Applied Mathematics},
  mrclass  = {68T05 (62J02)},
  mrnumber = {2592278},
  url      = {https://doi.org/10.1016/j.cam.2009.11.059},
}

Xin Guo 郭昕

Publications

Competitive Research Grants

Teaching