Momiao Xiong

Kai Zhang, Shan Liu, Momiao Xiong

A coordinate system is a foundation for every quantitative science, engineering, and medicine. Classical physics and statistics are based on the Cartesian coordinate system. The classical probability and hypothesis testing theory can only be applied to Euclidean data. However, modern data in the real world are from natural language processing, mathematical formulas, social networks, transportation and sensor networks, computer visions, automations, and biomedical measurements. The Euclidean assumption is not appropriate for non Euclidean data. This perspective addresses the urgent need to overcome those fundamental limitations and encourages extensions of classical probability theory and hypothesis testing , diffusion models and stochastic differential equations from Euclidean space to non Euclidean space. Artificial intelligence such as natural language processing, computer vision, graphical neural networks, manifold regression and inference theory, manifold learning, graph neural networks, compositional diffusion models for automatically compositional generations of concepts and demystifying machine learning systems, has been rapidly developed. Differential manifold theory is the mathematic foundations of deep learning and data science as well. We urgently need to shift the paradigm for data analysis from the classical Euclidean data analysis to both Euclidean and non Euclidean data analysis and develop more and more innovative methods for describing, estimating and inferring non Euclidean geometries of modern real datasets. A general framework for integrated analysis of both Euclidean and non Euclidean data, composite AI, decision intelligence and edge AI provide powerful innovative ideas and strategies for fundamentally advancing AI. We are expected to marry statistics with AI, develop a unified theory of modern statistics and drive next generation of AI and data science.

Tao Xu, Dung-Yang Lee, Momiao Xiong

Multi-step reasoning is a fundamental challenge in artificial intelligence, with applications ranging from mathematical problem-solving to decision-making in dynamic environments. Reinforcement Learning (RL) has shown promise in enabling agents to perform multi-step reasoning by optimizing long-term rewards. However, conventional RL methods struggle with complex reasoning tasks due to issues such as credit assignment, high-dimensional state representations, and stability concerns. Recent advancements in Transformer architectures and hyperbolic geometry have provided novel solutions to these challenges. This paper introduces a new framework that integrates hyperbolic Transformers into RL for multi-step reasoning. The proposed approach leverages hyperbolic embeddings to model hierarchical structures effectively. We present theoretical insights, algorithmic details, and experimental results that include Frontier Math and nonlinear optimal control problems. Compared to RL with vanilla transformer, the hyperbolic RL largely improves accuracy by (32%~44%) on FrontierMath benchmark, (43%~45%) on nonlinear optimal control benchmark, while achieving impressive reduction in computational time by (16%~32%) on FrontierMath benchmark, (16%~17%) on nonlinear optimal control benchmark. Our work demonstrates the potential of hyperbolic Transformers in reinforcement learning, particularly for multi-step reasoning tasks that involve hierarchical structures.

Lerong Li, Momiao Xiong

Realizations of stochastic process are often observed temporal data or functional data. There are growing interests in classification of dynamic or functional data. The basic feature of functional data is that the functional data have infinite dimensions and are highly correlated. An essential issue for classifying dynamic and functional data is how to effectively reduce their dimension and explore dynamic feature. However, few statistical methods for dynamic data classification have directly used rich dynamic features of the data. We propose to use second order ordinary differential equation (ODE) to model dynamic process and principal differential analysis to estimate constant or time-varying parameters in the ODE. We examine differential dynamic properties of the dynamic system across different conditions including stability and transient-response, which determine how the dynamic systems maintain their functions and performance under a broad range of random internal and external perturbations. We use the parameters in the ODE as features for classifiers. As a proof of principle, the proposed methods are applied to classifying normal and abnormal QRS complexes in the electrocardiogram (ECG) data analysis, which is of great clinical values in diagnosis of cardiovascular diseases. We show that the ODE-based classification methods in QRS complex classification outperform the currently widely used neural networks with Fourier expansion coefficients of the functional data as their features. We expect that the dynamic model-based classification methods may open a new avenue for functional data classification.

Getie Zewdie, Momiao Xiong

Portable, Wearable and Wireless electrocardiogram (ECG) Systems have the potential to be used as point-of-care for cardiovascular disease diagnostic systems. Such wearable and wireless ECG systems require automatic detection of cardiovascular disease. Even in the primary care, automation of ECG diagnostic systems will improve efficiency of ECG diagnosis and reduce the minimal training requirement of local healthcare workers. However, few fully automatic myocardial infarction (MI) disease detection algorithms have well been developed. This paper presents a novel automatic MI classification algorithm using second order ordinary differential equation (ODE) with time varying coefficients, which simultaneously captures morphological and dynamic feature of highly correlated ECG signals. By effectively estimating the unobserved state variables and the parameters of the second order ODE, the accuracy of the classification was significantly improved. The estimated time varying coefficients of the second order ODE were used as an input to the support vector machine (SVM) for the MI classification. The proposed method was applied to the PTB diagnostic ECG database within Physionet. The overall sensitivity, specificity, and classification accuracy of 12 lead ECGs for MI binary classifications were 98.7%, 96.4% and 98.3%, respectively. We also found that even using one lead ECG signals, we can reach accuracy as high as 97%. Multiclass MI classification is a challenging task but the developed ODE approach for 12 lead ECGs coupled with multiclass SVM reached 96.4% accuracy for classifying 5 subgroups of MI and healthy controls.

Momiao Xiong, Long Ma

Fast and cheaper next generation sequencing technologies will generate unprecedentedly massive and highly-dimensional genomic and epigenomic variation data. In the near future, a routine part of medical record will include the sequenced genomes. A fundamental question is how to efficiently extract genomic and epigenomic variants of clinical utility which will provide information for optimal wellness and interference strategies. Traditional paradigm for identifying variants of clinical validity is to test association of the variants. However, significantly associated genetic variants may or may not be usefulness for diagnosis and prognosis of diseases. Alternative to association studies for finding genetic variants of predictive utility is to systematically search variants that contain sufficient information for phenotype prediction. To achieve this, we introduce concepts of sufficient dimension reduction and coordinate hypothesis which project the original high dimensional data to very low dimensional space while preserving all information on response phenotypes. We then formulate clinically significant genetic variant discovery problem into sparse SDR problem and develop algorithms that can select significant genetic variants from up to or even ten millions of predictors with the aid of dividing SDR for whole genome into a number of subSDR problems defined for genomic regions. The sparse SDR is in turn formulated as sparse optimal scoring problem, but with penalty which can remove row vectors from the basis matrix. To speed up computation, we develop the modified alternating direction method for multipliers to solve the sparse optimal scoring problem which can easily be implemented in parallel. To illustrate its application, the proposed method is applied to simulation data and the NHLBI's Exome Sequencing Project dataset