KAUST Ph.D. student Jian Cao received a best paper award from the American Statistical Association (ASA) for his paper on computing high-dimensional normal and Student-t probabilities. The paper uses Tile-Low-Rank Quasi-Monte Carlo and Block Reordering. Cao, a member of Professor Marc Genton's group, will be recognized at the ASA's Joint Statistical Meetings. Why it matters: This award highlights KAUST's strength in high-performance computing and statistical research, contributing to advancements in handling complex, high-dimensional datasets.
This talk discusses the asymptotic study of large asymmetric spiked tensor models. It explores connections between these models and equivalent random matrices constructed through contractions of the original tensor. Mohamed El Amine Seddik, currently a senior researcher at TII in Abu Dhabi, presented the work. Why it matters: The research provides theoretical foundations relevant to machine learning algorithms that leverage low-rank tensor structures, potentially impacting AI research and applications in the region.
This article discusses approximating a high-dimensional distribution using Gaussian variational inference by minimizing Kullback-Leibler divergence. It builds upon previous research and approximates the minimizer using a Gaussian distribution with specific mean and variance. The study details approximation accuracy and applicability using efficient dimension, relevant for analyzing sampling schemes in optimization. Why it matters: This theoretical research can inform the development of more efficient and accurate AI algorithms, particularly in areas dealing with high-dimensional data such as machine learning and data analysis.
A presentation will demonstrate the construction of well-calibrated, distribution-free neural Temporal Point Process (TPP) models from multiple event sequences using conformal prediction. The method builds a distribution-free joint prediction region for event arrival time and type with a finite-sample coverage guarantee. The refined method is based on the highest density regions, derived from the joint predictive density of event arrival time and type to address the challenge of creating a joint prediction region for a bivariate response that includes both continuous and discrete data types. Why it matters: This research from a KAUST postdoc improves uncertainty quantification in neural TPPs, which are crucial for modeling continuous-time event sequences, with applications in various fields, by providing more reliable prediction regions.
This paper introduces neural Bayes estimators for censored peaks-over-threshold models, enhancing computational efficiency in spatial extremal dependence modeling. The method uses data augmentation to encode censoring information in the neural network input, challenging traditional likelihood-based approaches. The estimators were applied to assess extreme particulate matter concentrations over Saudi Arabia, demonstrating efficacy in high-dimensional models. Why it matters: The research offers a computationally efficient alternative for environmental modeling and risk assessment in the region.
MBZUAI is hosting an "AI Quorum on Statistics for the Future of AI" in Abu Dhabi, focusing on the intersection of statistics and AI in healthcare. Organized by Professors Tian Zheng (Columbia University) and Hongtu Zhu (UNC), the event gathers experts from top global universities and organizations like Eli Lilly and MD Anderson Cancer Center. The workshop aims to integrate statistical insights into AI research, fostering innovations in the field. Why it matters: By convening international experts, MBZUAI is positioning itself as a hub for interdisciplinary AI research with a focus on healthcare applications.
Gaurav Agarwal, a statistics Ph.D. student in the Environmental Statistics Group at KAUST, is researching statistical methods with environmental applications, such as understanding salt tolerance in plants. He is developing a user-friendly web application to make these methods accessible to those with limited statistical backgrounds. Agarwal also focuses on data visualization and outlier detection techniques for quality control of radiosonde wind data. Why it matters: This research contributes to environmental science by providing accessible statistical tools and methods for analyzing complex environmental data, potentially aiding in addressing challenges like plant resilience and climate monitoring.
This paper introduces a novel fuzzy clustering method for circular time series based on a new dependence measure that considers circular arcs. The algorithm groups series generated from similar stochastic processes and demonstrates computational efficiency. The method is applied to time series of wind direction in Saudi Arabia, showcasing its practical potential.