Workshops Organization:


  • Integration of Deep Learning Theories at NIPS 2018, Palais des Congrès de Montréal, Canada.
    — Co-organize with Professor Richard Baraniuk, Stephane Mallat, Anima Anandkumar, and Ankit Patel.

Conferences, Seminars, and Workshops Presentations:


  • [75] On excess mass behavior in Gaussian mixture models with Orlicz Wasserstein distances. Workshop on "Interpretable inference via principled Bayesian nonparametric approaches in biomedical research & beyond", National University of Singapore (NUS), 2024 (Invited talk).

  • [74] On the multivariate Fourier integral theorem: Statistical and methodological perspectives. International Conference on Econometrics and Statistics (EcoSta), Tokyo, Japan, 2023 (Invited talk).

  • [73] Bayesian sieves and excess mass behaviors in Dirichlet Process mixture models. Workshop on "Approximation Methods in Bayesian Analysis", Centre International de Rencontres Mathématiques, Marseille, France, 2023 (Invited talk).

  • [72] On the multivariate Fourier integral theorem: Statistical and methodological perspectives. Vietnam Institute for Advanced Study in Mathematics (VIASM), 2023 (Invited talk).

  • [71] On the multivariate Fourier integral theorem: Statistical and methodological perspectives. Summer School Series on Mathematical Statistics and Machine Learning: 2023 School on Bayesian Statistics and Computation, Ho Chi Minh, Viet Nam, 2023 (Invited talk).

  • [70] Optimal transport in machine learning and data science. Machine Learning Lunch Seminar, Vanderbilt University, 2023 (Invited talk).

  • [69] Probabilistic frameworks for understanding self-attention mechanism in Transformer. Applied Statistics Symposium, International Chinese Statistical Association (ICSA), 2023 (Invited talk).

  • [68] Instability, statistical accuracy, and computational efficiency. Applied Math Colloquium, University of California, Los Angeles (UCLA), 2022 (Invited talk).

  • [67] Instability, statistical accuracy, and computational efficiency. Workshop on Structured Optimization Models in High-Dimensional Data Analysis, National University of Singapore (NUS), 2022 (Invited talk).

  • [66] Optimal transport in machine learning and data science. Optimal Transport and Mean Field games Seminar, University of California, Los Angeles (UCLA), 2022 (Invited talk).

  • [65] Statistical and computational perspectives on mixture models. Department Seminar, INRIA, France, 2022 (Invited talk).

  • [64] Instability, statistical accuracy, and computational efficiency. Department Seminar, Department of Computer Science, Monash University, Australia, 2022 (Invited talk).

  • [63] Statistical and computational perspectives on mixture models. Department Seminar, Department of Mathematics and Statistics, University of Queensland, Australia, 2022 (Invited talk).

  • [62] Instability, statistical accuracy, and computational efficiency. Department Seminar, Department of Statistics, University of Sydney, Australia, 2022 (Invited talk).

  • [61] Optimal transport in machine learning and data science. Applied Artificial Intelligence Institute, Deakin University, Australia, 2022 (Invited talk).

  • [60] Optimal transport in machine learning and data science. Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, CA, USA, 2022 (Invited talk).

  • [59] Bayesian sieves and excess mass behaviors in Dirichlet Process mixture models. 13th International Conference on Bayesian Nonparametrics, Pontificia Universidad Católica de Chile, 2022 (Invited talk).

  • [58] Optimization in machine learning and data science. Department Seminar, College of Engineering and Computer Science, VinUni, Ha Hoi, Vietnam, 2022 (Invited talk).

  • [57] Optimal transport in large-scale machine learning applications. FPT Software AI Center, Ha Noi, Viet Nam, 2022 (Invited talk).

  • [56] Optimal transport in large-scale machine learning applications. Viettel AI Center, Ha Noi, Viet Nam, 2022 (Invited talk).

  • [55] On the multivariate Fourier integral theorem: Statistical and methodological perspectives. International Conference on Econometrics and Statistics (EcoSta), Kyoto, Japan, 2022 (Invited talk).

  • [54] Bayesian sieves and excess mass behaviors in Dirichlet Process mixture models. 49th Annual Meeting of the Statistical Society of Canada, Simon Fraser University, Canada, 2022 (Invited talk).

  • [53] Bayesian sieves and excess mass behaviors in Dirichlet Process mixture models. Optimal transport meets Bayes" workshop, 16th World Meeting of the International Society for Bayesian Analysis, 2022 (Invited talk).

  • [52] On multimarginal partial optimal transport: equivalent forms and computational complexity. SIAM Imaging conference, 2022 (Invited talk).

  • [51] Instability, statistical accuracy, and computational efficiency. BLISS Seminar, Department of Electrical Engineering and Computer Sciences, UC Berkeley, 2021 (Invited talk).

  • [50] On optimal transport in machine learning and data science. The 13th Asian Conference in Machine Learning, 2021 (Tutorial Talk).

  • [49] On optimal transport in machine learning and data science. The Online Asian Machine Learning School, 2021 (Invited talk).

  • [48] On optimal transport in machine learning and data science: computational, modeling, and theoretical perspective. INFORMS, 2021 (Invited talk).

  • [47] Statistical efficiency of parameter estimation in generalized contaminated models. International Indian Statistical Association (IISA) Conference, 2021 (Invited talk).

  • [46] Statistical efficiency of parameter estimation in generalized contaminated models. International Chinese Statistical Association (ICSA), Xi'an University, Xi’an, China, 2021 (Invited talk - Cancelled due to COVID-19).

  • [45] Statistical efficiency of parameter estimation in generalized contaminated models. International Conference on Econometrics and Statistics (EcoSta), Yonsei University, Seoul, South Korea, 2021 (Invited talk).

  • [44] Statistical and computational perspectives on latent variable models. Department of Decision Sciences at Bocconi University, Italy, 2020 (Invited talk).

  • [43] Convergence rates for Gaussian mixtures of experts. International Indian Statistical Association (IISA) Conference, University of Illinois at Chicago, 2020 (Invited talk - Cancelled due to COVID-19).

  • [42] Statistical and computational perspectives on latent variable models. Young Data Science Researcher Seminar, ETH Zurich, 2020 (Invited talk).

  • [41] Statistical and computational perspectives on latent variable models. Department Seminar, Department of Biostatistics, University of California, Berkeley, 2020 (Invited talk).

  • [40] Statistical and computational perspectives on latent variable models. Department Seminar, Department of Statistics and Data Science, CMU, 2020 (Invited talk).

  • [39] Statistical and computational perspectives on latent variable models. Department Seminar, Department of Statistics, University of California, Los Angeles, 2020 (Invited talk).

  • [38] Statistical and computational perspectives on latent variable models. Department Seminar, Department of Statistics and Data Science, Cornell University, 2020 (Invited talk).

  • [37] Statistical and computational perspectives on latent variable models. Department Seminar, Department of Statistics, Rutgers University, 2020 (Invited talk).

  • [36] Statistical and computational perspectives on latent variable models. Department Seminar, Department of Statistics, Purdue University, 2020 (Invited talk).

  • [35] Statistical and computational perspectives on latent variable models. Department Seminar, Department of Data Science, University of California, San Diego, 2020 (Invited talk).

  • [34] Statistical and computational perspectives on latent variable models. Department Seminar, Department of Data Science, John Hopskins University, 2020 (Invited talk).

  • [33] Statistical and computational perspectives on latent variable models. Department Seminar, Department of Statistics, University of Wisconsin, Madison, 2020 (Invited talk).

  • [32] Statistical and computational perspectives on latent variable models. Department Seminar, Department of Statistics, Duke University, 2020 (Invited talk).

  • [31] Statistical and computational perspectives on latent variable models. Department Seminar, Department of Statistical Science, University of Toronto, 2020 (Invited talk).

  • [30] Statistical and computational perspectives on latent variable models. Department Seminar, Department of Statistics and Data Sciences, University of Texas, Austin, 2020 (Invited talk).

  • [29] Statistical and computational perspectives on latent variable models. Department Seminar, Department of Statistics, University of Illinois, Urbana-Champaign, 2020 (Invited talk).

  • [28] Statistical and computational perspectives on latent variable models. Department Seminar, Booth School of Management, University of Southern California, 2020 (Invited talk).

  • [27] Statistical and computational perspectives on latent variable models. Department Seminar, Department of Data Science and Operation Research, University of Southern California, 2020 (Invited talk).

  • [26] Statistical and computational perspectives on latent variable models. Department Seminar, Department of Statistics, University of Southern California, 2020 (Invited talk).

  • [25] Statistical and computational perspectives on latent variable models. Department Seminar, Department of Statistics, North Carolina State University, 2020 (Invited talk).

  • [24] Statistical and computational perspectives on latent variable models. Department Seminar, Department of Statistics, University of Minnesota, Twin Cities, 2020 (Invited talk).

  • [23] Statistical and computational perspectives on latent variable models. Department Seminar, Krannert School of Management, Purdue University, 2020 (Invited talk).

  • [22] Statistical and computational perspectives on latent variable models. Department Seminar, Department of Statistics, Pennsylvania State University, 2020 (Invited talk).

  • [21] On multilayer latent variable models: Computational and statistical perspectives. Mathematics of Data and Decisions Seminar, Department of Mathematics, UC Davis, 2019 (Invited talk).

  • [20] On optimal transport in machine learning and statistics: Computational, modeling, and theoretical perspectives. Research seminar, VinAI Research, Ha Noi, 2019 (Invited talk).

  • [19] Statistical and computational perspective of mixture and hierarchical models. BLISS Seminar, Department of EECS, UC Berkeley, 2019 (Invited talk).

  • [18] Singularity structures of mixture models: Statistical and computational perspective. Joint Statistical Meetings (JSM), Denver, Colorado, 2019 (Invited talk).

  • [17] On efficient optimal transport: an analysis of greedy and accelerated mirror descent algorithms. International Conference on Machine Learning (ICML), Long Beach, CA, 2019.

  • [16] Singularity structures of mixture models: Statistical and computational perspective. Department Seminar, Department of Electrical Engineering and Computer Sciences, Rice, November, 2018, Houston, Texas (Invited talk).

  • [15] Singularity structures of parameter estimation in finite mixtures of distributions. Joint Stanford and Berkeley Applied Math Event, November 2018, University of California, Berkeley (Invited talk).

  • [14] Singularity Structure of Parameter Space and Posterior Contraction in Finite Mixture Models. Joint Statistical Meetings (JSM), August, 2017, Baltimore, Maryland (Invited talk).

  • [13] Singularity structures and parameter estimation behavior in finite mixtures of distributions. Nonparametric Statistics Workshop: Integration of Theory, Methods, and Applications, October, 2016, Ann Arbor, Michigan.

  • [12] Singularity structures and impacts on parameter estimation in finite mixtures of distributions. Shannon Centennial Symposium, September, 2016, Ann Arbor, Michigan.

  • [11] Singularity structures and parameter estimation behavior in finite mixtures of distributions. Joint Statistical Meetings (JSM), August, 2016, Chicago, Illinois.

  • [10] Singularity structures and parameter estimation behavior in finite mixtures of distributions. Conference on Statistical Learning and Data Science, June, 2016, University of North Carolina at the Chapel Hill.

  • [9] Singularity structures and parameter estimation behavior in finite mixtures of distributions. Statistical Machine Learning Student Workshop, June, 2016, University of Michigan, Ann Arbor.

  • [8] Singularity structures and parameter estimation in mixtures of skew normal distributions. Michigan Student Symposium for Interdisciplinary Statistical Sciences (MSSISS), March, 2016, Ann Arbor, MI.

  • [7] Weak identifiability and convergence rate of mixing measures in over-fitted Gaussian mixture models. Student Seminar, Department of Statistics, University of Michigan, January, 2016, Ann Arbor, Michigan.

  • [6] Intrinsic difficulties for the inference of mixing measures in finite mixtures of univariate skew normal distributions. From Industrial Statistics to Data Science, October, 2015, Ann Arbor, Michigan.

  • [5] Posterior concentration of mixing parameters in some weakly identifiable finite mixture models. 10th Conference on Bayesian Nonparametrics, June, 2015, Raleigh, North Carolina.

  • [4] Weak identifiability and optimal rate of convergence of mixing measures in over-fitted Gaussian mixture models. Statistical Machine Learning Student Workshop, June, 2015, University of Michigan, Ann Arbor.

  • [3] Weak identifiability and optimal rate of convergence of mixing measures in over-fitted Gaussian mixture models. NSF Conference - Statistics for Complex Systems, June, 2015, Madison, Wisconsin.

  • [2] Optimal convergence rate of parameter estimation in overfitted finite Gaussian mixture models. Michigan Student Symposium for Interdisciplinary Statistical Sciences (MSSISS), March, 2015, Ann Arbor, MI.

  • [1] Identifiability and convergence rate of parameter estimations in exact-fitted finite mixture models. Statistical Machine Learning Student Workshop, June, 2014, University of Michigan, Ann Arbor.

Talk Slides