Lexin Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Lexin Li has a total of 80 co-authors. Here are the top co-authors by number of shared publications:
- Jian Kang
Department of Biostatistics, University of Michigan
4 shared publications Chengchun Shi
Department of Statistics, London School of Economics and Political Science , London WC2A 2AE
3 shared publications- Chengchun Shi
London School of Economics and Political Science
3 shared publications Xiang Lyu
Division of Biostatistics, University of California , Berkeley, CA 94720
3 shared publicationsXiaowu Dai
Department of Economics, University of California, Berkeley, CA
3 shared publicationsYin Xia
Department of Statistics, School of Management, Fudan University, 220 Handan Rd, Wu Jiao Chang, Yangpu, Shanghai 200433, China
3 shared publications
Latest Publications
- Open Access
- 27 August 2026
- Published by Taylor & Francis in Journal of the American Statistical Association
- p. 1-58
Semi-pessimistic Reinforcement Learning
1 IntroductionReinforcement learning (RL) aims to train an intelligent agent to make optimal decisions in a given environment to maximize some long-term reward. It provides a powerful paradigm for ...
- 27 August 2026
- Published by Taylor & Francis in Journal of the American Statistical Association
- p. 1-58
Open AccessSemi-pessimistic Reinforcement Learning
1 IntroductionReinforcement learning (RL) aims to train an intelligent agent to make optimal decisions in a given environment to maximize some long-term reward. It provides a powerful paradigm for ...
- 13 April 2026
- Published by Oxford University Press (OUP) in Journal of the Royal Statistical Society Series B: Statistical Methodology
- Vol. 88 (5) , 1556-1577
Generalized point process additive models
In this article, we propose a generalized point process additive model with a scalar response and high-dimensional point process predictors. Our proposal is built upon four key components: a realization of a point process as a random counting measure, a generalized point process regression framework, a new kernel function for random measure through kernel embedding, and a suite of low-dimensional structures including the additive model, reduced basis representation, and sparsity. We develop an efficient penalized likelihood procedure for model estimation, and establish both the estimation consistency and selection consistency of the estimator, while allowing the number of point process predictors to diverge. We illustrate and evaluate our method through simulations and an electronic health record data application.
- 13 April 2026
- Published by Oxford University Press (OUP) in Journal of the Royal Statistical Society Series B: Statistical Methodology
- Vol. 88 (5) , 1556-1577
Generalized point process additive models
In this article, we propose a generalized point process additive model with a scalar response and high-dimensional point process predictors. Our proposal is built upon four key components: a realization of a point process as a random counting measure, a generalized point process regression framework, a new kernel function for random measure through kernel embedding, and a suite of low-dimensional structures including the additive model, reduced basis representation, and sparsity. We develop an efficient penalized likelihood procedure for model estimation, and establish both the estimation consistency and selection consistency of the estimator, while allowing the number of point process predictors to diverge. We illustrate and evaluate our method through simulations and an electronic health record data application.
- 3 April 2026
- Published by Taylor & Francis in Journal of the American Statistical Association
- Vol. 121 (554) , 867-870
Discussion of “The ICML 2023 Ranking Experiment: Examining Author Self-Assessment in ML/AI Peer Review”
1. We would like to congratulate Su et al. on this timely and important paper, which presents a carefully designed and empirically grounded study of author self-assessment in the context of large-s...
- 3 April 2026
- Published by Taylor & Francis in Journal of the American Statistical Association
- Vol. 121 (554) , 867-870
Discussion of “The ICML 2023 Ranking Experiment: Examining Author Self-Assessment in ML/AI Peer Review”
1. We would like to congratulate Su et al. on this timely and important paper, which presents a carefully designed and empirically grounded study of author self-assessment in the context of large-s...
- 27 January 2026
- Published by Springer Nature in Statistics in Biosciences
Fairness-Aware Kidney Exchange and Kidney Paired Donation
- 27 January 2026
- Published by Springer Nature in Statistics in Biosciences
Fairness-Aware Kidney Exchange and Kidney Paired Donation
- Open Access
- 16 December 2025
- Published by Oxford University Press (OUP) in Brain
- Vol. 149 (8) , 2702-2715
Cortico-basal oscillations index naturalistic movements during deep brain stimulation
The basal ganglia and sensorimotor cortex are essential nodes of a network that supports motor control. In Parkinson’s disease, disruptions in this network lead to rigidity and slowness during movement execution. Deep brain stimulation (DBS) of the basal ganglia has proved effective in alleviating Parkinson’s disease-related hypokinetic symptoms, and sensing-enabled neurostimulators now afford the opportunity to detect cortico-basal oscillations during motion. However, the specific contributions of these motor network nodes to chronic, naturalistic movement and the effects of DBS on circuit dynamics are not well understood. To address these gaps, we recorded >530 h of cortical and subcortical signals from 15 Parkinson’s disease patients (27 hemispheres) during unsupervised, unconstrained daily activities and subthalamic or pallidal DBS. Synchronized wrist-worn accelerometers tracked forearm speeds, supporting the evaluation of neural biomarkers related to motion. Our study validated and extended the known relationship between cortical and subcortical beta power (13–30 Hz) and movement. We showed that cortical low (13–20 Hz) and high (21–30 Hz) beta movement-related desynchronization effectively distinguished between mobile and stationary states. In the subthalamic nucleus and globus pallidus interna, high beta movement-related desynchronization and gamma (40–80 Hz) movement-related synchronization exhibited significant group-level correlations with movement kinematics. When stimulated at 130 Hz, cortical stimulation-entrained gamma oscillations at the half-harmonic (∼65 Hz) were observed. Furthermore, cortical entrained gamma movement-related synchronization was a stronger predictor of motion than broadband gamma movement-related synchronization. We developed machine learning models to predict naturalistic movement over extended periods using spectral features from brief neural recordings (0.5–8 s epochs). Cortical models outperformed subcortical models, although combining cortico-basal signals yielded the highest model performance (area under the curve > 0.85 for binary movement state classifiers; Pearson’s r statistic > 0.68 for continuous forearm speed regressors). Higher DBS current amplitudes were associated with reduced beta movement-related desynchronization and low gamma (40–60 Hz) movement-related synchronization in the subthalamic nucleus and globus pallidus interna. This negatively impacted the accuracy of the subcortical models, whereas cortical and cortico-basal model performance remained stable across stimulation amplitudes. Our study demonstrates that cortico-basal nodes of the motor network encode complementary kinematic information, which can be integrated to enhance the accuracy and stability of chronic, naturalistic movement decoding during deep brain stimulation. These insights support the development and integration of therapeutic brain–computer interfaces with closed-loop, adaptive DBS to leverage rapid and precise movement-predictive models for the treatment of motor network disorders.
- 16 December 2025
- Published by Oxford University Press (OUP) in Brain
- Vol. 149 (8) , 2702-2715
Open AccessCortico-basal oscillations index naturalistic movements during deep brain stimulation
The basal ganglia and sensorimotor cortex are essential nodes of a network that supports motor control. In Parkinson’s disease, disruptions in this network lead to rigidity and slowness during movement execution. Deep brain stimulation (DBS) of the basal ganglia has proved effective in alleviating Parkinson’s disease-related hypokinetic symptoms, and sensing-enabled neurostimulators now afford the opportunity to detect cortico-basal oscillations during motion. However, the specific contributions of these motor network nodes to chronic, naturalistic movement and the effects of DBS on circuit dynamics are not well understood. To address these gaps, we recorded >530 h of cortical and subcortical signals from 15 Parkinson’s disease patients (27 hemispheres) during unsupervised, unconstrained daily activities and subthalamic or pallidal DBS. Synchronized wrist-worn accelerometers tracked forearm speeds, supporting the evaluation of neural biomarkers related to motion. Our study validated and extended the known relationship between cortical and subcortical beta power (13–30 Hz) and movement. We showed that cortical low (13–20 Hz) and high (21–30 Hz) beta movement-related desynchronization effectively distinguished between mobile and stationary states. In the subthalamic nucleus and globus pallidus interna, high beta movement-related desynchronization and gamma (40–80 Hz) movement-related synchronization exhibited significant group-level correlations with movement kinematics. When stimulated at 130 Hz, cortical stimulation-entrained gamma oscillations at the half-harmonic (∼65 Hz) were observed. Furthermore, cortical entrained gamma movement-related synchronization was a stronger predictor of motion than broadband gamma movement-related synchronization. We developed machine learning models to predict naturalistic movement over extended periods using spectral features from brief neural recordings (0.5–8 s epochs). Cortical models outperformed subcortical models, although combining cortico-basal signals yielded the highest model performance (area under the curve > 0.85 for binary movement state classifiers; Pearson’s r statistic > 0.68 for continuous forearm speed regressors). Higher DBS current amplitudes were associated with reduced beta movement-related desynchronization and low gamma (40–60 Hz) movement-related synchronization in the subthalamic nucleus and globus pallidus interna. This negatively impacted the accuracy of the subcortical models, whereas cortical and cortico-basal model performance remained stable across stimulation amplitudes. Our study demonstrates that cortico-basal nodes of the motor network encode complementary kinematic information, which can be integrated to enhance the accuracy and stability of chronic, naturalistic movement decoding during deep brain stimulation. These insights support the development and integration of therapeutic brain–computer interfaces with closed-loop, adaptive DBS to leverage rapid and precise movement-predictive models for the treatment of motor network disorders.
Subgroup Mediation Analysis
Imaging genetics–based mediation analysis provides a powerful approach to understanding gene–brain–cognition pathways. However, despite recent progress, several challenges involving group‐level and subject‐level heterogeneity remain largely unaddressed. In this article, we develop a new model and the associated methodology for imaging genetics–based subgroup mediation analysis. Our key idea is to equip a system of structural equation models with conditional Gaussian graphical models, and we allow both the mean and precision matrix to vary based on individual covariates, which in turn define a set of latent clusters. As a result, our model can simultaneously identify gene–brain–cognition pathways, uncover brain connectivity network structures, handle high‐dimensional multivariate mediators and incorporate both group‐level and subject‐level heterogeneity. We carry out simulations to demonstrate the efficacy of our proposed method and further illustrate the method with an image genetics study of Alzheimer's disease.
Subgroup Mediation Analysis
Imaging genetics–based mediation analysis provides a powerful approach to understanding gene–brain–cognition pathways. However, despite recent progress, several challenges involving group‐level and subject‐level heterogeneity remain largely unaddressed. In this article, we develop a new model and the associated methodology for imaging genetics–based subgroup mediation analysis. Our key idea is to equip a system of structural equation models with conditional Gaussian graphical models, and we allow both the mean and precision matrix to vary based on individual covariates, which in turn define a set of latent clusters. As a result, our model can simultaneously identify gene–brain–cognition pathways, uncover brain connectivity network structures, handle high‐dimensional multivariate mediators and incorporate both group‐level and subject‐level heterogeneity. We carry out simulations to demonstrate the efficacy of our proposed method and further illustrate the method with an image genetics study of Alzheimer's disease.
- Open Access
Structural Classification of Locally Stationary Time Series Based on Second-order Characteristics
Time series classification is crucial for numerous scientific and engineering applications. In this article, we present a numerically efficient, practically competitive, and theoretically rigorous classification method for distinguishing between two classes of locally stationary time series based on their time-domain, second-order characteristics. Our approach builds on the autoregressive approximation for locally stationary time series, combined with an ensemble aggregation and a distance-based threshold for classification. It imposes no requirement on the training sample size, and is shown to achieve zero misclassification error rate asymptotically when the underlying time series differ only mildly in their second-order characteristics. The new method is demonstrated to outperform a variety of state-of-the-art solutions, including wavelet-based, tree-based, convolution-based methods, as well as modern deep learning methods, through intensive numerical simulations and a real EEG data analysis for epilepsy classification.
Open AccessStructural Classification of Locally Stationary Time Series Based on Second-order Characteristics
Time series classification is crucial for numerous scientific and engineering applications. In this article, we present a numerically efficient, practically competitive, and theoretically rigorous classification method for distinguishing between two classes of locally stationary time series based on their time-domain, second-order characteristics. Our approach builds on the autoregressive approximation for locally stationary time series, combined with an ensemble aggregation and a distance-based threshold for classification. It imposes no requirement on the training sample size, and is shown to achieve zero misclassification error rate asymptotically when the underlying time series differ only mildly in their second-order characteristics. The new method is demonstrated to outperform a variety of state-of-the-art solutions, including wavelet-based, tree-based, convolution-based methods, as well as modern deep learning methods, through intensive numerical simulations and a real EEG data analysis for epilepsy classification.
- Open Access
Leveraging genomic large language models to enhance causal genotype-brain-clinical pathways in Alzheimer’s disease
Genome-wide association studies (GWAS) have identified numerous Alzheimer’s disease (AD)- associated variants. However, how these variants contribute to the etiology of AD remains largely elusive. Recent advances in genomic large language models (LLMs) offer new opportunities to interpret the genetic variation observed in personal genome. In this study, we propose epiBrainLLM, a novel computational framework that leverages genomic LLM to enhance our understanding of the causal pathways from genotypes to brain measures to AD-related clinical phenotypes. epiBrainLLM will first convert the personal DNA sequence into a diverse set of genomic and epigenomic features using a pretrained genomic LLM and then use these features to further predict phenotypes. Across various experimental settings, epiBrainLLM significantly improves causal analysis compared to traditional genotype association approach. We conclude that epiBrainLLM provides a novel perspective for understanding the regulatory mechanisms underlying the AD disease etiology, potentially offering insights into complex disease mechanisms beyond AD.
Open AccessLeveraging genomic large language models to enhance causal genotype-brain-clinical pathways in Alzheimer’s disease
Genome-wide association studies (GWAS) have identified numerous Alzheimer’s disease (AD)- associated variants. However, how these variants contribute to the etiology of AD remains largely elusive. Recent advances in genomic large language models (LLMs) offer new opportunities to interpret the genetic variation observed in personal genome. In this study, we propose epiBrainLLM, a novel computational framework that leverages genomic LLM to enhance our understanding of the causal pathways from genotypes to brain measures to AD-related clinical phenotypes. epiBrainLLM will first convert the personal DNA sequence into a diverse set of genomic and epigenomic features using a pretrained genomic LLM and then use these features to further predict phenotypes. Across various experimental settings, epiBrainLLM significantly improves causal analysis compared to traditional genotype association approach. We conclude that epiBrainLLM provides a novel perspective for understanding the regulatory mechanisms underlying the AD disease etiology, potentially offering insights into complex disease mechanisms beyond AD.
- Open Access
- 27 March 2024
- Published by Oxford University Press (OUP) in Biometrics
- Vol. 80 (2)
High-dimensional multisubject time series transition matrix inference with application to brain connectivity analysis
ASTRACT: Brain-effective connectivity analysis quantifies directed influence of one neural element or region over another, and it is of great scientific interest to understand how effective connectivity pattern is affected by variations of subject conditions. Vector autoregression (VAR) is a useful tool for this type of problems. However, there is a paucity of solutions when there is measurement error, when there are multiple subjects, and when the focus is the inference of the transition matrix. In this article, we study the problem of transition matrix inference under the high-dimensional VAR model with measurement error and multiple subjects. We propose a simultaneous testing procedure, with three key components: a modified expectation-maximization (EM) algorithm, a test statistic based on the tensor regression of a bias-corrected estimator of the lagged auto-covariance given the covariates, and a properly thresholded simultaneous test. We establish the uniform consistency for the estimators of our modified EM, and show that the subsequent test achieves both a consistent false discovery control, and its power approaches one asymptotically. We demonstrate the efficacy of our method through both simulations and a brain connectivity study of task-evoked functional magnetic resonance imaging.
- 27 March 2024
- Published by Oxford University Press (OUP) in Biometrics
- Vol. 80 (2)
Open AccessHigh-dimensional multisubject time series transition matrix inference with application to brain connectivity analysis
ASTRACT: Brain-effective connectivity analysis quantifies directed influence of one neural element or region over another, and it is of great scientific interest to understand how effective connectivity pattern is affected by variations of subject conditions. Vector autoregression (VAR) is a useful tool for this type of problems. However, there is a paucity of solutions when there is measurement error, when there are multiple subjects, and when the focus is the inference of the transition matrix. In this article, we study the problem of transition matrix inference under the high-dimensional VAR model with measurement error and multiple subjects. We propose a simultaneous testing procedure, with three key components: a modified expectation-maximization (EM) algorithm, a test statistic based on the tensor regression of a bias-corrected estimator of the lagged auto-covariance given the covariates, and a properly thresholded simultaneous test. We establish the uniform consistency for the estimators of our modified EM, and show that the subsequent test achieves both a consistent false discovery control, and its power approaches one asymptotically. We demonstrate the efficacy of our method through both simulations and a brain connectivity study of task-evoked functional magnetic resonance imaging.
- Open Access
Post-Regularization Confidence Bands for Ordinary Differential Equations
Ordinary differential equation (ODE) is an important tool to study the dynamics of a system of biological and physical processes. A central question in ODE modeling is to infer the significance of individual regulatory effect of one signal variable on another. However, building confidence band for ODE with unknown regulatory relations is challenging, and it remains largely an open question. In this article, we construct post-regularization confidence band for individual regulatory function in ODE with unknown functionals and noisy data observations. Our proposal is the first of its kind, and is built on two novel ingredients. The first is a new localized kernel learning approach that combines reproducing kernel learning with local Taylor approximation, and the second is a new de-biasing method that tackles infinite-dimensional functionals and additional measurement errors. We show that the constructed confidence band has the desired asymptotic coverage probability, and the recovered regulatory network approaches the truth with probability tending to one. We establish the theoretical properties when the number of variables in the system can be either smaller or larger than the number of sampling time points, and we study the regime-switching phenomenon. We demonstrate the efficacy of the proposed method through both simulations and illustrations with two data applications.
Open AccessPost-Regularization Confidence Bands for Ordinary Differential Equations
Ordinary differential equation (ODE) is an important tool to study the dynamics of a system of biological and physical processes. A central question in ODE modeling is to infer the significance of individual regulatory effect of one signal variable on another. However, building confidence band for ODE with unknown regulatory relations is challenging, and it remains largely an open question. In this article, we construct post-regularization confidence band for individual regulatory function in ODE with unknown functionals and noisy data observations. Our proposal is the first of its kind, and is built on two novel ingredients. The first is a new localized kernel learning approach that combines reproducing kernel learning with local Taylor approximation, and the second is a new de-biasing method that tackles infinite-dimensional functionals and additional measurement errors. We show that the constructed confidence band has the desired asymptotic coverage probability, and the recovered regulatory network approaches the truth with probability tending to one. We establish the theoretical properties when the number of variables in the system can be either smaller or larger than the number of sampling time points, and we study the regime-switching phenomenon. We demonstrate the efficacy of the proposed method through both simulations and illustrations with two data applications.