arXiv subjects

Michael Lingzhi Li

Publications and source records attributed to Michael Lingzhi Li.

At least 19 recordsLinked to original sources

arXiv2026

Safe Meta-Policy Design with Risk Control

Models can be retrained as new data arrive, but deploying every new version risks replacing a good policy with a worse one. We study how to plan policy updates (i.e., meta-policy) before future candidates are trained, balancing the benefits of improvement against the risk of performance regression. Our offline meta-policy maximizes expected cumulative value subject to a budget on the expected number of updates that perform worse than the policies they replace. We estimate the value and risk of possible switches from historical learning trajectories, represent an update schedule as a path in a directed acyclic graph, and select a schedule using dynamic programming. A leading-order analysis identifies the signal-to-noise ratio of policy improvement as a key driver of update frequency, waiting times, and risk allocation: clearer improvements support earlier, more frequent updates, while noisier improvements call for longer waits or greater risk expenditure. Their asymptotic rates also reveal a diminishing marginal cost of achieving greater safety over time. Experiments on synthetic and clinical trial data illustrate the performance--risk tradeoff and compare our method with alternative baselines.

stat.ML↗

arXiv2026

Balancing Optimality and Diversity: Human-Centered Decision Making through Generative Curation

Many decision-support systems recommend actions by optimizing measurable objectives, even when a human decision-maker retains final authority and considers additional criteria that are difficult to specify in advance. We study how an algorithm should curate a small portfolio of quantitatively strong alternatives in such settings. We introduce generative curation, a framework that learns a recommendation policy to maximize the expected desirability of the action ultimately selected by the decision-maker. For policies that generate quantitatively competitive actions, we decompose expected portfolio desirability into quantitative performance and a qualitative curation gain. Under a Gaussian process model of residual desirability, this gain is characterized by the Gaussian width induced by the covariance kernel, yielding a decision-theoretic notion of diversity based on qualitative nonredundancy rather than generic geometric separation. We establish diminishing returns to portfolio size and characterize regimes in which optimal policies are balanced, endpoint-concentrated, or space-filling. We develop neural generative and sequential optimization approaches applicable to continuous and combinatorial action spaces. Controlled synthetic experiments demonstrate substantial regret reductions relative to optimization- and distance-based benchmarks, while an Atlanta police redistricting case study illustrates the framework's applicability to a complex operational planning problem.

cs.LG↗

arXiv2026

The Greedy Advantage in Finite-Horizon Bandits

Organizations increasingly rely on sequential experimentation to improve decision-making. While the multi-armed bandit literature has developed algorithms with strong asymptotic regret guarantees, many practical applications operate over finite and externally imposed horizons. Motivated by the finite-horizon setting, we develop a class of regularized greedy algorithms for multi-armed Bernoulli bandits. We derive the first finite-horizon regret envelopes for regularized greedy bandits, showing that finite-horizon regret decomposes into transient exploration costs and a suboptimal convergence term that decays exponentially with the regularization strength. This characterization yields principled calibration rules for the regularization parameters and, as a limiting case, sharper regret guarantees for the classical greedy policy. Across extensive numerical experiments, calibrated regularized greedy policies consistently match or outperform state-of-the-art algorithms. These results suggest that regularized greedy policies can provide an effective approach for finite-horizon bandit problems.

stat.ML↗

arXiv2026

Dr. DocBench: A Comprehensive Benchmark for Expert-Level and Difficult Document Parsing

Document parsing and recognition are fundamental capabilities for vision-language models (VLMs) and document processing systems. However, existing Optical Character Recognition (OCR) and document parsing benchmarks are increasingly limited in coverage and difficulty: many focus on common document genres or uniformly sampled pages where modern parsers already perform strongly, while offering limited annotation for expert-domain structures such as chemical formula, music notation, complex tables, and cross-page layouts. We introduce Dr. DocBench, a difficulty-aware benchmark for expert-level document parsing. Built from a large-scale multilingual book corpus, Dr. DocBench spans 52 BISAC subject domains and selects challenging documents through parser-failure-based sampling, targeting cases where multiple state-of-the-art systems struggle. It contains 4,514 annotated pages from long documents averaging around 100 pages, with 65k high-quality page- and block-level annotations for layout, reading order, hierarchical relations, and domain-specific visual contents. Evaluations of pipeline-based parsers and general-purpose VLMs show that strong performance on existing benchmarks does not transfer to our expert-level document parsing. Our analysis reveals substantial failures across subjects, content types, and structural attributes, highlighting Dr. DocBench as a comprehensive testbed for diagnosing and advancing document intelligence.

cs.CL↗

arXiv2026

Learning to Cover: Online Learning and Optimization with Irreversible Decisions

We define an online learning and optimization problem with discrete and irreversible decisions contributing toward a coverage target. In each period, a decision-maker selects facilities to open, receives information on the success of each one, and updates a classification model to guide future decisions. The goal is to minimize facility openings under a chance constraint reflecting the coverage target, in an asymptotic regime characterized by a large target number of facilities $m\to\infty$ but a finite horizon $T \in \mathcal{Z}_+$. We prove that, under statistical conditions, the online classifier converges to the Bayes-optimal classifier at a rate of at best $\mathcal{O}(1/\sqrt n)$. Thus, we formulate our online learning and optimization problem, with a generalized learning rate $r>0$ and a residual error $1-p$. We derive an asymptotically optimal algorithm and an asymptotically tight lower bound. The regret grows in $Θ\left(m^{\frac{1-r}{1-r^T}}\right)$ if $p=1$ (perfect learning) or in $Θ\left(\max\left\{m^{\frac{1-r}{1-r^T}},\sqrt{m}\right\}\right)$ otherwise; in particular, the regret rate is sub-linear and converges exponentially fast to its infinite-horizon limit. We extend this result to a more complicated facility location setting in a bipartite facility-customer graph with a target on customer coverage. Throughout, constructive proofs identify a policy featuring limited exploration initially and fast exploitation later on once uncertainty gets mitigated. These results uncover the benefits of limited online learning and optimization through pilot programs prior to full-fledged expansion.

cs.LG↗

arXiv2025

The CRITICAL Records Integrated Standardization Pipeline (CRISP): End-to-End Processing of Large-scale Multi-institutional OMOP CDM Data

While existing critical care EHR datasets such as MIMIC and eICU have enabled significant advances in clinical AI research, the CRITICAL dataset opens new frontiers by providing extensive scale and diversity -- containing 1.95 billion records from 371,365 patients across four geographically diverse CTSA institutions. CRITICAL's unique strength lies in capturing full-spectrum patient journeys, including pre-ICU, ICU, and post-ICU encounters across both inpatient and outpatient settings. This multi-institutional, longitudinal perspective creates transformative opportunities for developing generalizable predictive models and advancing health equity research. However, the richness of this multi-site resource introduces substantial complexity in data harmonization, with heterogeneous collection practices and diverse vocabulary usage patterns requiring sophisticated preprocessing approaches. We present CRISP to unlock the full potential of this valuable resource. CRISP systematically transforms raw Observational Medical Outcomes Partnership Common Data Model data into ML-ready datasets through: (1) transparent data quality management with comprehensive audit trails, (2) cross-vocabulary mapping of heterogeneous medical terminologies to unified SNOMED-CT standards, with deduplication and unit standardization, (3) modular architecture with parallel optimization enabling complete dataset processing in $<$1 day even on standard computing hardware, and (4) comprehensive baseline model benchmarks spanning multiple clinical prediction tasks to establish reproducible performance standards. By providing processing pipeline, baseline implementations, and detailed transformation documentation, CRISP saves researchers months of preprocessing effort and democratizes access to large-scale multi-institutional critical care data, enabling them to focus on advancing clinical AI.

cs.LG↗

arXiv2025

Statistical Performance Guarantee for Subgroup Identification with Generic Machine Learning

Across a wide array of disciplines, many researchers use machine learning (ML) algorithms to identify a subgroup of individuals who are likely to benefit from a treatment the most (``exceptional responders'') or those who are harmed by it. A common approach to this subgroup identification problem consists of two steps. First, researchers estimate the conditional average treatment effect (CATE) using an ML algorithm. Next, they use the estimated CATE to select those individuals who are predicted to be most affected by the treatment, either positively or negatively. Unfortunately, CATE estimates are often biased and noisy. In addition, utilizing the same data to both identify a subgroup and estimate its group average treatment effect results in a multiple testing problem. To address these challenges, we develop uniform confidence bands for estimation of the group average treatment effect sorted by generic ML algorithm (GATES). Using these uniform confidence bands, researchers can identify, with a statistical guarantee, a subgroup whose GATES exceeds a certain effect size, regardless of how this effect size is chosen. The validity of the proposed methodology depends solely on randomization of treatment and random sampling of units. Importantly, our method does not require modeling assumptions and avoids a computationally intensive resampling procedure. A simulation study shows that the proposed uniform confidence bands are reasonably informative and have an appropriate empirical coverage even when the sample size is as small as 100. We analyze a clinical trial of late-stage prostate cancer and find a relatively large proportion of exceptional responders.

stat.ME↗

arXiv2025

Cramming Contextual Bandits for On-policy Statistical Evaluation

We introduce the cram method as a general statistical framework for evaluating the final learned policy from a multi-armed contextual bandit algorithm, using the dataset generated by the same bandit algorithm. The proposed on-policy evaluation methodology differs from most existing methods that focus on off-policy performance evaluation of contextual bandit algorithms. Cramming utilizes an entire bandit sequence through a single pass of data, leading to both statistically and computationally efficient evaluation. We prove that if a bandit algorithm satisfies a certain stability condition, the resulting crammed evaluation estimator is consistent and asymptotically normal under mild regularity conditions. Furthermore, we show that this stability condition holds for commonly used linear contextual bandit algorithms, including epsilon-greedy, Thompson Sampling, and Upper Confidence Bound algorithms. Using both synthetic and publicly available datasets, we compare the empirical performance of cramming with the state-of-the-art methods. The results demonstrate that the proposed cram method reduces the evaluation standard error by approximately 40% relative to off-policy evaluation methods while preserving unbiasedness and valid confidence interval coverage.

cs.LG↗

arXiv2025

Comment on "Generic machine learning inference on heterogeneous treatment effects in randomized experiments."

We analyze the split-sample robust inference (SSRI) methodology proposed by Chernozhukov, Demirer, Duflo, and Fernandez-Val (CDDF) for quantifying uncertainty in heterogeneous treatment effect estimation. While SSRI effectively accounts for randomness in data splitting, its computational cost can be prohibitive when combined with complex machine learning (ML) models. We present an alternative randomization inference (RI) approach that maintains SSRI's generality without requiring repeated data splitting. By leveraging cross-fitting and design-based inference, RI achieves valid confidence intervals while significantly reducing computational burden. We compare the two methods through simulation, demonstrating that RI retains statistical efficiency while being more practical for large-scale applications.

stat.ME↗

arXiv2024

Neyman Meets Causal Machine Learning: Experimental Evaluation of Individualized Treatment Rules

A century ago, Neyman showed how to evaluate the efficacy of treatment using a randomized experiment under a minimal set of assumptions. This classical repeated sampling framework serves as a basis of routine experimental analyses conducted by today's scientists across disciplines. In this paper, we demonstrate that Neyman's methodology can also be used to experimentally evaluate the efficacy of individualized treatment rules (ITRs), which are derived by modern causal machine learning algorithms. In particular, we show how to account for additional uncertainty resulting from a training process based on cross-fitting. The primary advantage of Neyman's approach is that it can be applied to any ITR regardless of the properties of machine learning algorithms that are used to derive the ITR. We also show, somewhat surprisingly, that for certain metrics, it is more efficient to conduct this ex-post experimental evaluation of an ITR than to conduct an ex-ante experimental evaluation that randomly assigns some units to the ITR. Our analysis demonstrates that Neyman's repeated sampling framework is as relevant for causal inference today as it has been since its inception.

stat.ME↗

arXiv2024

Statistical Inference for Heterogeneous Treatment Effects Discovered by Generic Machine Learning in Randomized Experiments

Researchers are increasingly turning to machine learning (ML) algorithms to investigate causal heterogeneity in randomized experiments. Despite their promise, ML algorithms may fail to accurately ascertain heterogeneous treatment effects under practical settings with many covariates and small sample size. In addition, the quantification of estimation uncertainty remains a challenge. We develop a general approach to statistical inference for heterogeneous treatment effects discovered by a generic ML algorithm. We apply the Neyman's repeated sampling framework to a common setting, in which researchers use an ML algorithm to estimate the conditional average treatment effect and then divide the sample into several groups based on the magnitude of the estimated effects. We show how to estimate the average treatment effect within each of these groups, and construct a valid confidence interval. In addition, we develop nonparametric tests of treatment effect homogeneity across groups, and rank-consistency of within-group average treatment effects. The validity of our methodology does not rely on the properties of ML algorithms because it is solely based on the randomization of treatment assignment and random sampling of units. Finally, we generalize our methodology to the cross-fitting procedure by accounting for the additional uncertainty induced by the random splitting of data.

stat.ME↗

arXiv2023

Benchmarking Large Language Models on CMExam -- A Comprehensive Chinese Medical Exam Dataset

Recent advancements in large language models (LLMs) have transformed the field of question answering (QA). However, evaluating LLMs in the medical field is challenging due to the lack of standardized and comprehensive datasets. To address this gap, we introduce CMExam, sourced from the Chinese National Medical Licensing Examination. CMExam consists of 60K+ multiple-choice questions for standardized and objective evaluations, as well as solution explanations for model reasoning evaluation in an open-ended manner. For in-depth analyses of LLMs, we invited medical professionals to label five additional question-wise annotations, including disease groups, clinical departments, medical disciplines, areas of competency, and question difficulty levels. Alongside the dataset, we further conducted thorough experiments with representative LLMs and QA algorithms on CMExam. The results show that GPT-4 had the best accuracy of 61.6% and a weighted F1 score of 0.617. These results highlight a great disparity when compared to human accuracy, which stood at 71.6%. For explanation tasks, while LLMs could generate relevant reasoning and demonstrate improved performance after finetuning, they fall short of a desired standard, indicating ample room for improvement. To the best of our knowledge, CMExam is the first Chinese medical exam dataset to provide comprehensive medical annotations. The experiments and findings of LLM evaluation also provide valuable insights into the challenges and potential solutions in developing Chinese medical QA systems and LLM evaluation pipelines. The dataset and relevant code are available at https://github.com/williamliujl/CMExam.

cs.CL↗

arXiv2023

Branch-and-Price for Prescriptive Contagion Analytics

Predictive contagion models are ubiquitous in epidemiology, social sciences, engineering, and management. This paper formulates a prescriptive contagion analytics model where a decision-maker allocates shared resources across multiple segments of a population, each governed by continuous-time dynamics. We define four real-world problems under this umbrella: vaccine distribution, vaccination centers deployment, content promotion, and congestion mitigation. These problems feature a large-scale mixed-integer non-convex optimization structure with constraints governed by ordinary differential equations, combining the challenges of discrete optimization, non-linear optimization, and continuous-time system dynamics. This paper develops a branch-and-price methodology for prescriptive contagion analytics based on: (i) a set partitioning reformulation; (ii) a column generation decomposition; (iii) a state-clustering algorithm for discrete-decision continuous-state dynamic programming; and (iv) a tri-partite branching scheme to circumvent non-linearities. Extensive experiments show that the algorithm scales to very large and otherwise-intractable instances, outperforming state-of-the-art benchmarks. Our methodology provides practical benefits in contagion systems; in particular, it can increase the effectiveness of a vaccination campaign by an estimated 12-70%, resulting in 7,000 to 12,000 extra saved lives over a three-month horizon mirroring the COVID-19 pandemic. We provide an open-source implementation of the methodology in an online repository to enable replication.

math.OC↗

arXiv2023

Holistic Deep Learning

This paper presents a novel holistic deep learning framework that simultaneously addresses the challenges of vulnerability to input perturbations, overparametrization, and performance instability from different train-validation splits. The proposed framework holistically improves accuracy, robustness, sparsity, and stability over standard deep learning models, as demonstrated by extensive experiments on both tabular and image data sets. The results are further validated by ablation experiments and SHAP value analysis, which reveal the interactions and trade-offs between the different evaluation metrics. To support practitioners applying our framework, we provide a prescriptive approach that offers recommendations for selecting an appropriate training loss function based on their specific objectives. All the code to reproduce the results can be found at https://github.com/kimvc7/HDL.

cs.LG↗

arXiv2023

Distributionally Robust Causal Inference with Observational Data

We consider the estimation of average treatment effects in observational studies and propose a new framework of robust causal inference with unobserved confounders. Our approach is based on distributionally robust optimization and proceeds in two steps. We first specify the maximal degree to which the distribution of unobserved potential outcomes may deviate from that of observed outcomes. We then derive sharp bounds on the average treatment effects under this assumption. Our framework encompasses the popular marginal sensitivity model as a special case, and we demonstrate how the proposed methodology can address a primary challenge of the marginal sensitivity model that it produces uninformative results when unobserved confounders substantially affect treatment and outcome. Specifically, we develop an alternative sensitivity model, called the distributional sensitivity model, under the assumption that heterogeneity of treatment effect due to unobserved variables is relatively small. Unlike the marginal sensitivity model, the distributional sensitivity model allows for potential lack of overlap and often produces informative bounds even when unobserved variables substantially affect both treatment and outcome. Finally, we show how to extend the distributional sensitivity model to difference-in-differences designs and settings with instrumental variables. Through simulation and empirical studies, we demonstrate the applicability of the proposed methodology.

stat.ME↗

arXiv2021

Where to locate COVID-19 mass vaccination facilities?

The outbreak of COVID-19 led to a record-breaking race to develop a vaccine. However, the limited vaccine capacity creates another massive challenge: how to distribute vaccines to mitigate the near-end impact of the pandemic? In the United States in particular, the new Biden administration is launching mass vaccination sites across the country, raising the obvious question of where to locate these clinics to maximize the effectiveness of the vaccination campaign. This paper tackles this question with a novel data-driven approach to optimize COVID-19 vaccine distribution. We first augment a state-of-the-art epidemiological model, called DELPHI, to capture the effects of vaccinations and the variability in mortality rates across age groups. We then integrate this predictive model into a prescriptive model to optimize the location of vaccination sites and subsequent vaccine allocation. The model is formulated as a bilinear, non-convex optimization model. To solve it, we propose a coordinate descent algorithm that iterates between optimizing vaccine distribution and simulating the dynamics of the pandemic. As compared to benchmarks based on demographic and epidemiological information, the proposed optimization approach increases the effectiveness of the vaccination campaign by an estimated $20\%$, saving an extra $4000$ extra lives in the United States over a three-month period. The proposed solution achieves critical fairness objectives -- by reducing the death toll of the pandemic in several states without hurting others -- and is highly robust to uncertainties and forecast errors -- by achieving similar benefits under a vast range of perturbations.

q-bio.PE↗

arXiv2021

Experimental Evaluation of Individualized Treatment Rules

The increasing availability of individual-level data has led to numerous applications of individualized (or personalized) treatment rules (ITRs). Policy makers often wish to empirically evaluate ITRs and compare their relative performance before implementing them in a target population. We propose a new evaluation metric, the population average prescriptive effect (PAPE). The PAPE compares the performance of ITR with that of non-individualized treatment rule, which randomly treats the same proportion of units. Averaging the PAPE over a range of budget constraints yields our second evaluation metric, the area under the prescriptive effect curve (AUPEC). The AUPEC represents an overall performance measure for evaluation, like the area under the receiver and operating characteristic curve (AUROC) does for classification, and is a generalization of the QINI coefficient utilized in uplift modeling. We use Neyman's repeated sampling framework to estimate the PAPE and AUPEC and derive their exact finite-sample variances based on random sampling of units and random assignment of treatment. We extend our methodology to a common setting, in which the same experimental data is used to both estimate and evaluate ITRs. In this case, our variance calculation incorporates the additional uncertainty due to random splits of data used for cross-validation. The proposed evaluation metrics can be estimated without requiring modeling assumptions, asymptotic approximation, or resampling methods. As a result, it is applicable to any ITR including those based on complex machine learning algorithms. The open-source software package is available for implementing the proposed methodology.

stat.AP↗

arXiv2021

Stochastic Cutting Planes for Data-Driven Optimization

We introduce a stochastic version of the cutting-plane method for a large class of data-driven Mixed-Integer Nonlinear Optimization (MINLO) problems. We show that under very weak assumptions the stochastic algorithm is able to converge to an $ε$-optimal solution with high probability. Numerical experiments on several problems show that stochastic cutting planes is able to deliver a multiple order-of-magnitude speedup compared to the standard cutting-plane method. We further experimentally explore the lower limits of sampling for stochastic cutting planes and show that for many problems, a sampling size of $O(\sqrt[3]{n})$ appears to be sufficient for high quality solutions.

math.OC↗