arXiv subjects

Didong Li

Publications and source records attributed to Didong Li.

At least 19 recordsLinked to original sources

arXiv2026

The Fidelity and Feedback Traps: The Case for Health Digital Twins as Modular Evolving Causal Systems

Digital twins for health may be used to compare treatments, project patient trajectories, and support clinical decisions. While related to mechanical digital twins, those initially developed for engineering applications, replicating the mechanical digital twin architecture and goals may fail in health for two reasons. The fidelity trap is the belief that an accurate model can answer what-if questions by virtue of its accuracy. Prediction and counterfactual reasoning are different tasks, and a twin that can fit past trajectories well may miss the mark when ranking treatments. The feedback trap arises when the twin updates on data its own recommendations helped generate. Refitting in this way can recover a biased relationship and grow more confident even as data grows thinner. We contend that health digital twins should be conceived as causally valid, modular, and evolving systems. Modularity isolates the data and models needed for interventional recommendations, causal validity supports such claims, and governed evolution updates the twin while accounting for how its recommendations reshape the data. We conclude that the standard for a health twin should be how well it supports decisions in the world it helps create, not how faithfully it reproduces the world it observes.

stat.OT↗

arXiv2026

Mitigating Batch Effects in Histopathology via Language-Mediated Robust Embedding Generation

Pathology foundation models (PFMs) have demonstrated strong potential across clinical and scientific applications, yet their performance is often hindered by batch effects, which are non-biological variations across tissue source institutions (TSIs) that distort learned feature representations and impair generalization. Conventional mitigation strategies, such as stain normalization, offer limited success in addressing these high-dimensional, complex artifacts. We present GLMP (General-purpose LLM-Mediated Pathology model), a novel framework that generates robust numerical embeddings from histology image patches through an intermediate textual representation. By leveraging pretrained general-purpose multimodal large language models (MLLMs) and text encoders, GLMP effectively prioritizes biologically meaningful signals over TSI-specific artifacts, thereby improving cross-institutional generalization. To our knowledge, GLMP is the first pathology model to use text descriptions of histological features as an intermediate representation for generating numerical embeddings from histology images. Our results highlight the untapped potential of broad-domain, non-specialized MLLMs in computational pathology and introduce a new paradigm for building versatile, generalizable, and robust pathology models.

cs.CV↗

arXiv2026

Rejoinder: The ICML 2023 Ranking Experiment: Examining Author Self-Assessment in ML/AI Peer Review

This article is the rejoinder to ``The ICML 2023 Ranking Experiment: Examining Author Self-Assessment in ML/AI Peer Review,'' to appear in the Journal of the American Statistical Association with discussion. To address the practical and theoretical points raised by the discussants, we organize our response around four core themes: (i) formulating peer review as a statistical estimation problem; (ii) mitigating equity and strategic concerns in the deployment of the Isotonic Mechanism; (iii) incorporating complementary signals such as reviewer rankings and structured metadata; and (iv) exploring a human-centered framework for peer review in the era of generative AI.

stat.AP↗

arXiv2026

Hierarchical Probabilistic Principal Component Analysis of Longitudinal Data

In many longitudinal studies, a large number of variables are measured repeatedly over time, with substantial missing data. Existing methods, such as probabilistic principal component analysis (PPCA), are ill-equipped to handle such incomplete, high-dimensional longitudinal data, as they fail to account for the nested sources of variation and temporal dependency inherent in repeated measures. We introduce hierarchical probabilistic principal component analysis (HPPCA), a two-level probabilistic factor model that explicitly separates between-subject variance from time-varying within-subject dynamics. The within-subject latent factors are modeled by a Gaussian process. We develop an EM algorithm to handle missing data and flexible covariance kernels, accelerated by computationally efficient initializers. Simulation studies demonstrated that HPPCA robustly recovers model parameters subspaces and substantially outperforms both standard PPCA and multivariate functional PCA in imputation accuracy, even under heavy missingness and model misspecification. An application to the long COVID symptoms in the Researching COVID to Enhance Recovery adult cohort revealed that HPPCA effectively captured the data's hierarchical structure and its learned features significantly improved the prediction of clinical outcomes and the recovery of masked clinical records compared to exisiting methods.

stat.ME↗

arXiv2026

Understanding Overparametrization in Survival Models through Interpolation

Classical statistical learning theory predicts a U-shaped relationship between test loss and model capacity, driven by the bias-variance trade-off. Recent advances in modern machine learning have revealed a more complex pattern, double-descent, in which test loss, after peaking near the interpolation threshold, decreases again as model capacity continues to grow. While this behavior has been extensively analyzed in regression and classification, its manifestation in survival analysis remains unexplored. This study investigates overparametrization in four representative survival models: DeepSurv, PC-Hazard, Nnet-Survival, and N-MTLR. We rigorously define interpolation and finite-norm interpolation, two key characteristics of loss-based models to understand double-descent. We then show the existence (or absence) of (finite-norm) interpolation of all four models. Our findings clarify how likelihood-based losses and model implementation jointly determine the feasibility of interpolation and show that overparametrization should not be regarded as benign for survival models. All theoretical results are supported by numerical experiments that highlight the distinct generalization behaviors of survival models.

stat.ML↗

arXiv2026

NIH-MPINet: A Large-Scale Feature-Rich Network Dataset for Mapping the Frontiers of Team Science

This study presents a large-scale network dataset, NIH-MPINet, curated from NIH RePORTER and PubMed, characterizing collaboration among multiple Principal Investigators (multi-PIs) on NIH R01-equivalent grants from 2006 to 2023. The network characterizes 30,127 PIs as nodes and their collaborations on 86,743 NIH R01-equivalent grants as edges, spanning 888 recipient organizations and supported by 40 NIH Institutes and Centers. We also curated comprehensive metadata, including node-level features such as PI affiliation, alongside edge-level features comprising grant years, titles, and abstracts. Using these data, we constructed a PI collaboration network and identified 19 communities as well as 20 major research topics. Several collaboration communities showed distinct thematic profiles, such as cardiovascular health, cancer immunotherapy, neuroscience, and microbiome research, while genetics and genomics were broadly represented across communities. By incorporating temporal analysis, we observed shifts in research topics and collaboration patterns over time. Topics like healthcare and outcomes research, cognitive health, and Alzheimer's disease have become more prominent in recent years, whereas molecular and cellular biology has seen a relative decline. Overall, this work provides a high-fidelity, feature-rich resource for advancing statistical learning methods and network analysis-based discoveries in the study of long-term biomedical collaboration.

cs.DL↗

arXiv2026

Incorporating LLM Embeddings for Variation Across the Human Genome

Recent advances in large language model (LLM) embeddings have enabled powerful representations for biological data, but most applications to date focus on gene-level information. We present one of the first systematic frameworks to generate genetic variant-level embeddings across the entire human genome. Using curated annotations from FAVOR, ClinVar, and the GWAS Catalog, we construct functional text descriptions for 8.9 billion possible variants and generated embeddings at three scales: 1.5 million HapMap3/MEGA variants, 90 million imputed UK Biobank (UKB) variants, and 9 billion all possible variants. Embeddings were produced using general purpose models including both OpenAI's text-embedding-3-large and the open-source Qwen3-Embedding-0.6B models. Baseline quality control experiments demonstrate high predictive accuracy for variant-level properties, validating the embeddings as structured representations of genomic variation. We further apply them to real-world embedding-augmented genetic risk predictions that demonstrate the performance of using LLM embeddings in polygenic risk score (PRS) style predictions over the UK Biobank cohort data. These resources, publicly available on Hugging Face, provide a foundation for advancing large-scale genomic discovery and precision medicine.

stat.AP↗

arXiv2026

PrecLLM: A Privacy-Preserving Framework for Efficient Clinical Annotation Extraction from Unstructured EHRs using Small-Scale LLMs

Large Language Models (LLMs) have demonstrated remarkable proficiency in automated text annotation within natural language processing. However, their deployment in clinical settings is severely constrained by strict privacy regulations and the prohibitive computational cost of processing voluminous unstructured Electronic Health Records (EHRs). In this study, we developed a resource-efficient preprocessing technique that can be adopted in existing LLM procedures. This approach is particularly useful for smaller LLMs, which are often more accuracy-challenged, and forms a compact LLM framework optimized for local deployment in computational environments with stringent privacy requirements and restricted access to high-performance GPUs (PrecLLM). The preprocessing step includes both regular expressions (regex) and Retrieval-Augmented Generation (RAG) to extract and highlight key information from unstructured clinical notes. Pre-filtering long and unstructured texts enhanced the performance of smaller LLMs on EHR-related tasks. Evaluation was performed on two distinct cohorts: a locally curated private EHR dataset from the EPIC system for a Head and Neck Cancer (HNC) cohort, and the publicly available EHR dataset (MIMIC-IV). Using MIMIC-IV, we further compared PrecLLM against fine-tuned LLMs. Results demonstrated that PrecLLM substantially enhanced the performance of the original smaller LLMs in terms of sensitivity, specificity, and F1 scores, making it well-suited for privacy-sensitive and resource-constrained applications. This study offers optimized LLM performance for local, secure, and efficient healthcare applications, and provides practical guidance for clinical LLM deployment while addressing challenges related to privacy, computational feasibility, and clinical applicability.

cs.AI↗

arXiv2026

Can Generative Artificial Intelligence Survive Data Contamination? Theoretical Guarantees under Contaminated Recursive Training

As artificial intelligence (AI)-generated content proliferates, models are increasingly trained on their own outputs, risking progressive degradation or collapse. In this article, we provide the first positive, rigorous theoretical results, to the best of our knowledge, showing that under model-agnostic mild conditions, the model converges to the true data-generating distribution. The convergence rate is the minimum of the model's intrinsic rate and the fraction of real data at each training iteration, revealing a phase transition between data-limited and model-limited regimes. We further show that, for biased real data, correcting the bias prevents the persistence and amplification of early bias over training iteration. Extensive experiments across simulations, real images and texts validate our theoretical framework, establishing quantitative conditions for long-term AI stability in contaminated environments.

cs.LG↗

arXiv2026

On Statistical Inference for Rates of Change in Spatial Processes over Riemannian Manifolds

Statistical inference for spatial processes from partially realized or scattered data has seen voluminous developments in diverse areas ranging from environmental sciences to business and economics. Inference on the associated rates of change has seen some recent developments. The literature has been restricted to Euclidean domains, where inference is sought on directional derivatives, rates along a chosen direction of interest, at arbitrary locations. Inference for higher order rates, particularly directional curvature has also proved useful in these settings. Modern spatial data often arise from non-Euclidean domains. This manuscript particularly considers spatial processes defined over compact Riemannian manifolds. We develop a comprehensive inferential framework for spatial rates of change for such processes over vector fields. In doing so, we formalize smoothness of process realizations and construct differential processes -- the derivative and curvature processes. We derive conditions for kernels that ensure the existence of these processes and establish validity of the joint multivariate process consisting of the ``parent'' Gaussian process (GP) over the manifold and the associated differential processes. Predictive inference on these rates is devised conditioned on the realized process over the manifold. Manifolds arise as polyhedral meshes in practice. The success of our simulation experiments for assessing derivatives for processes observed over such meshes validate our theoretical findings. By enhancing our understanding of GPs on manifolds, this manuscript unlocks a variety of potential applications in machine learning and statistics where GPs have seen wide usage. We propose a fully model-based approach to inference on the differential processes arising from a spatial process from partially observed or realized data across scattered location on a manifold.

math.ST↗

arXiv2025

Difference-in-differences with stochastic policy shifts of a continuous treatment

Treatment effects of stochastic policy shifts quantify differences in outcomes across counterfactual scenarios with varying treatment distributions. Stochastic policy shifts may be of interest in settings where it is unrealistic or infeasible to deterministically manipulate treatments. In this paper, methods are developed to draw inference about stochastic policy effects under difference-in-differences (DiD) designs with a continuous treatment. The proposed causal estimand is the expected effect of modifying the continuous dose distribution among the treated, i.e., those that received a non-zero dose. Several possible stochastic policies are discussed and a general framework for identification and estimation is proposed. One stochastic policy applicable to many settings is the exponential tilt, which increments the conditional density function of the continuous dose. For the exponential tilt policy, a double/debiased machine learning estimator is proposed that allows for data-adaptive, nonparametric nuisance function estimation. Under mild convergence rate conditions, the estimator is shown to be root-$n$ consistent and asymptotically normal with variance attaining the nonparametric efficiency bound. The proposed method is used to study the effect of hydraulic fracturing activity on employment and income.

stat.ME↗

arXiv2025

How to Find Fantastic AI Papers: Self-Rankings as a Powerful Predictor of Scientific Impact Beyond Peer Review

Peer review in academic research aims not only to ensure factual correctness but also to identify work of high scientific potential that can shape future research directions. This task is especially critical in fast-moving fields such as artificial intelligence (AI), yet it has become increasingly difficult given the rapid growth of submissions. In this paper, we investigate an underexplored measure for identifying high-impact research: authors' own rankings of their multiple submissions to the same AI conference. Grounded in game-theoretic reasoning, we hypothesize that self-rankings are informative because authors possess unique understanding of their work's conceptual depth and long-term promise. To test this hypothesis, we conducted a large-scale experiment at a leading AI conference, where 1,342 researchers self-ranked their 2,592 submissions by perceived quality. Tracking outcomes over more than a year, we found that papers ranked highest by their authors received twice as many citations as their lowest-ranked counterparts; self-rankings were especially effective at identifying highly cited papers (those with over 150 citations). Moreover, we showed that self-rankings outperformed peer review scores in predicting future citation counts. Our results remained robust after accounting for confounders such as preprint posting time and self-citations. Together, these findings demonstrate that authors' self-rankings provide a reliable and valuable complement to peer review for identifying and elevating high-impact research in AI.

stat.AP↗

arXiv2025

Contrastive Dimension Reduction: A Systematic Review

Contrastive dimension reduction (CDR) methods aim to extract signal unique to or enriched in a treatment (foreground) group relative to a control (background) group. This setting arises in many scientific domains, such as genomics, imaging, and time series analysis, where traditional dimension reduction techniques such as Principal Component Analysis (PCA) may fail to isolate the signal of interest. In this review, we provide a systematic overview of existing CDR methods. We propose a pipeline for analyzing case-control studies together with a taxonomy of CDR methods based on their assumptions, objectives, and mathematical formulations, unifying disparate approaches under a shared conceptual framework. We highlight key applications and challenges in existing CDR methods, and identify open questions and future directions. By providing a clear framework for CDR and its applications, we aim to facilitate broader adoption and motivate further developments in this emerging field.

stat.ME↗

arXiv2025

Large-scale spatial variable gene atlas for spatial transcriptomics

Spatial variable genes (SVGs) reveal critical information about tissue architecture, cellular interactions, and disease microenvironments. As spatial transcriptomics (ST) technologies proliferate, accurately identifying SVGs across diverse platforms, tissue types, and disease contexts has become both a major opportunity and a significant computational challenge. Here, we present a comprehensive benchmarking study of 20 state-of-the-art SVG detection methods using human slides from STimage-1K4M, a large-scale resource of ST data comprising 662 slides from more than 18 tissue types. We evaluate each method across a range of biologically and technically meaningful criteria, including recovery of pathologist-annotated domain-specific markers, cross-slide reproducibility, scalability to high-resolution data, and robustness to technical variation. Our results reveal marked differences in performance depending on tissue type, spatial resolution, and study design. Beyond benchmarking, we construct the first cross-tissue atlas of SVGs, enabling comparative analysis of spatial gene programs across cancer and normal tissues. We observe similarities between pairs of tissues that reflect developmental and functional relationships, such as high overlap between thymus and lymph node, and uncover spatial gene programs associated with metastasis, immune infiltration, and tissue-of-origin identity in cancer. Together, our work defines a framework for evaluating and interpreting spatial gene expression and establishes a reference resource for the ST community.

stat.AP↗

arXiv2025

The ICML 2023 Ranking Experiment: Examining Author Self-Assessment in ML/AI Peer Review

We conducted an experiment during the review process of the 2023 International Conference on Machine Learning (ICML), asking authors with multiple submissions to rank their papers based on perceived quality. In total, we received 1,342 rankings, each from a different author, covering 2,592 submissions. In this paper, we present an empirical analysis of how author-provided rankings could be leveraged to improve peer review processes at machine learning conferences. We focus on the Isotonic Mechanism, which calibrates raw review scores using the author-provided rankings. Our analysis shows that these ranking-calibrated scores outperform the raw review scores in estimating the ground truth ``expected review scores'' in terms of both squared and absolute error metrics. Furthermore, we propose several cautious, low-risk applications of the Isotonic Mechanism and author-provided rankings in peer review, including supporting senior area chairs in overseeing area chairs' recommendations, assisting in the selection of paper awards, and guiding the recruitment of emergency reviewers.

stat.AP↗

arXiv2025

The Nearest-Neighbor Derivative Process: Modeling Spatial Rates of Change in Massive Datasets

Gaussian processes (GPs) are instrumental in modeling spatial processes, offering precise interpolation and prediction capabilities across fields such as environmental science and biology. Recently, there has been growing interest in extending GPs to infer spatial derivatives, which are vital for analyzing spatial dynamics and detecting subtle changes in data patterns. Despite their utility, traditional GPs suffer from computational inefficiencies, due to the cubic scaling with the number of spatial locations. Fortunately, the computational challenge has spurred extensive research on scalable GP methods. However, these scalable approaches do not directly accommodate the inference of derivative processes. A straightforward approach is to use scalable GP models followed by finite-difference methods, known as the plug-in estimator. This approach, while intuitive, suffers from sensitivity to parameter choices, and the approximate gradient may not be a valid GP, leading to compromised inference. To bridge this gap, we introduce the Nearest-Neighbor Derivative Process (NNDP), an innovative framework that models the spatial processes and their derivatives within a single scalable GP model. NNDP significantly reduces the computational time complexity from $O(n^3)$ to $O(n)$, making it feasible for large datasets. We provide various theoretical supports for NNDP and demonstrate its effectiveness through extensive simulations and real data analysis.

stat.ME↗

arXiv2025

Contrastive CUR: Interpretable Joint Feature and Sample Selection for Case-Control Studies

Dimension reduction is an essential tool for analyzing high dimensional data. Most existing methods, including principal component analysis (PCA), as well as their extensions, provide principal components that are often linear combinations of features, which are often challenging to interpret. CUR decomposition, another matrix decomposition technique, is a more interpretable and efficient alternative, offers simultaneous feature and sample selection. Despite this, many biomedical studies involve two groups: a foreground (treatment or case) group and a background (control) group, where the objective is to identify features unique to or enriched in the foreground. This need for contrastive dimension reduction is not well addressed by existing CUR methods, nor by contrastive approaches rooted in PCAs. Furthermore, they fail to address a key challenge in biomedical studies: the need for selecting samples unique to the foreground. In this paper, we address this gap by proposing a Contrastive CUR (CCUR), a novel method specifically designed for case-control studies. Through extensive experiments, we demonstrate that CCUR outperforms existing techniques in isolating biologically relevant features as well as identifying sample-specific responses unique to the foreground, offering deeper insights into case-control biomedical data.

stat.ME↗

arXiv2025

Kernel Density Bayesian Inverse Reinforcement Learning

Inverse reinforcement learning (IRL) methods infer an agent's reward function using demonstrations of expert behavior. A Bayesian IRL approach models a distribution over candidate reward functions, capturing a degree of uncertainty in the inferred reward function. This is critical in some applications, such as those involving clinical data. Typically, Bayesian IRL algorithms require large demonstration datasets, which may not be available in practice. In this work, we incorporate existing domain-specific data to achieve better posterior concentration rates. We study a common setting in clinical and biological applications where we have access to expert demonstrations and known reward functions for a set of training tasks. Our aim is to learn the reward function of a new test task given limited expert demonstrations. Existing Bayesian IRL methods impose restrictions on the form of input data, thus limiting the incorporation of training task data. To better leverage information from training tasks, we introduce kernel density Bayesian inverse reinforcement learning (KD-BIRL). Our approach employs a conditional kernel density estimator, which uses the known reward functions of the training tasks to improve the likelihood estimation across a range of reward functions and demonstration samples. Our empirical results highlight KD-BIRL's faster concentration rate in comparison to baselines, particularly in low test task expert demonstration data regimes. Additionally, we are the first to provide theoretical guarantees of posterior concentration for a Bayesian IRL algorithm. Taken together, this work introduces a principled and theoretically grounded framework that enables Bayesian IRL to be applied across a variety of domains.

cs.LG↗