Project Grant 2629216

CONFERENCE: THE FAST AND THE CURIOUS 3 (MIXING IN GAINESVILLE) - A WORKSHOP ON SCALABLE BAYESIAN INFERENCE AND HIGH-PERFORMANCE COMPUTATION -THIS AWARD SUPPORTS A WORKSHOP ON SCALABLE BAYESIAN INFERENCE AND HIGH-PERFORMANCE COMPUTATION THAT WILL BE HELD JANUARY 15-17, 2027, AT THE UNIVERSITY OF FLORIDA IN GAINESVILLE, FLORIDA. THIS WORKSHOP WILL BRING TOGETHER RESEARCHERS FROM STATISTICS, MACHINE LEARNING, SCIENTIFIC COMPUTING, AND RELATED DISCIPLINES TO ADDRESS THE GROWING CHALLENGES OF EFFICIENTLY ANALYZING INCREASINGLY LARGE AND COMPLEX DATASETS. MODERN SCIENTIFIC, ENGINEERING, AND SOCIETAL PROBLEMS OFTEN REQUIRE METHODS THAT CAN QUANTIFY UNCERTAINTY WHILE MAKING EFFECTIVE USE OF VAST AMOUNTS OF INFORMATION. THE WORKSHOP WILL PROVIDE A FORUM FOR SHARING NEW IDEAS, FOSTERING INTERDISCIPLINARY COLLABORATION, AND IDENTIFYING FUTURE RESEARCH OPPORTUNITIES. PARTICULAR EMPHASIS WILL BE PLACED ON SUPPORTING GRADUATE STUDENTS, POSTDOCTORAL SCHOLARS, AND EARLY-CAREER RESEARCHERS THROUGH OPPORTUNITIES FOR MENTORING, PROFESSIONAL DEVELOPMENT, AND SCIENTIFIC EXCHANGE. BY PROMOTING THE DEVELOPMENT AND DISSEMINATION OF MODERN COMPUTATIONAL AND STATISTICAL TOOLS, THE WORKSHOP WILL CONTRIBUTE TO ADVANCES IN DATA-DRIVEN DISCOVERY AND DECISION-MAKING ACROSS A WIDE RANGE OF APPLICATION AREAS. THE WORKSHOP WILL FOCUS ON RECENT ADVANCES IN SCALABLE BAYESIAN INFERENCE AND HIGH-PERFORMANCE COMPUTATION. TOPICS WILL INCLUDE SCALABLE MARKOV CHAIN MONTE CARLO METHODS, VARIATIONAL INFERENCE, STOCHASTIC GRADIENT APPROACHES, DISTRIBUTED AND FEDERATED BAYESIAN COMPUTATION, GPU-ACCELERATED ALGORITHMS, AND BAYESIAN METHODS FOR LARGE AND STREAMING DATASETS. DISCUSSIONS WILL ADDRESS THEORETICAL QUESTIONS CONCERNING CONVERGENCE, APPROXIMATION ACCURACY, ROBUSTNESS, AND COMPUTATIONAL EFFICIENCY, WHILE ALSO HIGHLIGHTING PRACTICAL IMPLEMENTATIONS AND APPLICATIONS IN FIELDS SUCH AS GENOMICS, NEUROSCIENCE, CLIMATE SCIENCE, ECONOMICS, AND MACHINE LEARNING. THE WORKSHOP WILL BRING TOGETHER RESEARCHERS WORKING ON THEORETICAL FOUNDATIONS, METHODOLOGICAL DEVELOPMENT, AND COMPUTATIONAL IMPLEMENTATION IN ORDER TO ADVANCE THE STATE OF THE ART IN SCALABLE BAYESIAN COMPUTATION AND IDENTIFY IMPORTANT DIRECTIONS FOR FUTURE RESEARCH. THE WEBSITE FOR THE CONFERENCE IS HTTPS://STAT.UFL.EDU/WINTER-WORKSHOP/2027-THE-FAST-AND-THE-CURIOUS-3-MIXING-IN-GAINESVILLE/ THIS AWARD REFLECTS NSF'S STATUTORY MISSION AND HAS BEEN DEEMED WORTHY OF SUPPORT THROUGH EVALUATION USING THE FOUNDATION'S INTELLECTUAL MERIT AND BROADER IMPACTS REVIEW CRITERIA.- SUBAWARDS ARE NOT PLANNED FOR THIS AWARD.