About

Dr. Raed Al Kontar is an associate professor in the Industrial and Operations Engineering department at the University of Michigan. He is also an affiliate with the Michigan Institutes for Data Science and Computational Discovery and Engineering. His research focuses on developing data science methods for solving engineering problems, with an emphasis on personalized and distributed data analytics. His work aims to effectively integrate knowledge from diverse data sources while maintaining data privacy and personalization, enabling sources to retain tailored models and decentralize inference. Dr. Al Kontar leads the Data Science Lab, which concentrates on probabilistic models and precision data science. His research has been highly recognized, with his group winning 12 best paper awards since 2022 across prominent organizations such as INFORMS, ASA, and IISE. His research is supported by notable agencies including the NSF, NIH, and NLM, as well as industry collaborators. His expertise encompasses areas such as energy and sustainability, health and human safety, and optimization, with a focus on federated learning, uncertainty quantification, digital twins, and heterogeneity in data sources.

Research topics

• Artificial Intelligence
• Computer Science
• Data Mining
• Mathematics
• Algorithm
• Machine Learning
• Computer Security
• Statistics
• Mathematical optimization
• Physics
• Data science

Selected publications

• Language-Induced Priors for Domain Adaptation

  ArXiv.org · 2026-05-14

  articleOpen accessSenior author

  Domain adaptation faces a fundamental paradox in the cold-start regime. When target data is scarce, statistical methods fail to distinguish relevant source domains from irrelevant ones, which often leads to negative transfer. In this paper, we address this challenge by leveraging expert textual descriptions of the target domain, a resource that is often available but overlooked. We propose a probabilistic framework that translates these semantic descriptions into a choice model, namely a Language-Induced Prior (LIP), that learns the preferences from a pretrained Large Language Model (LLM). The LIP is then integrated into an Expectation-Maximization algorithm to identify source relevance. Methodologically, this framework is compatible with any parametric model where a likelihood is available. It allows the LIP to guide the selection of sources when target signals are weak, while gradually refining these choices as samples accumulate. Theoretically, we prove that the estimator roughly matches an oracle cold-start MSE under a correct prior, while remaining asymptotically consistent regardless of the quality of the LIP. Empirically, we validated the framework on a descriptive (Gaussian estimation), a predictive (C-MAPSS dataset), and a prescriptive task (MuJoCo hopper).

  PublisherOA PDF

• SEE-OOD: Supervised Exploration for Enhanced Out-of-Distribution Detection

  Technometrics · 2026-05-12

  preprintOpen access

  Current techniques for Out-of-Distribution (OoD) detection predominantly rely on quantifying predictive uncertainty and incorporating model regularization during the training phase, using either real or synthetic OoD samples. However, methods that utilize real OoD samples lack exploration and are prone to overfit the OoD samples at hand. Whereas synthetic samples are often generated based on features extracted from training data, rendering them less effective when the training and OoD data are highly overlapped in the feature space. In this work, we propose a Wasserstein-score-based generative adversarial training scheme to enhance OoD detection accuracy, which, for the first time, performs data augmentation and exploration simultaneously under the supervision of limited OoD samples. Specifically, the generator explores OoD spaces and generates synthetic OoD samples using feedback from the discriminator, while the discriminator exploits both the observed and synthesized samples for OoD detection using a predefined Wasserstein score. We provide theoretical guarantees that the optimal solutions of our generative scheme are statistically achievable through adversarial training in empirical settings. We then demonstrate that the proposed method outperforms state-of-the-art techniques on various computer vision datasets and exhibits superior generalizability to unseen OoD data.

  PublisherOA PDFDOI

• Collaborative Contextual Bayesian Optimization

  ArXiv.org · 2026-04-20

  articleOpen accessSenior author

  Discovering optimal designs through sequential data collection is essential in many real-world applications. While Bayesian Optimization (BO) has achieved remarkable success in this setting, growing attention has recently turned to context-specific optimal design, formalized as Contextual Bayesian Optimization (CBO). Unlike BO, CBO is inherently more challenging as it must approximate an entire mapping from the context space to its corresponding optimal design, requiring simultaneous exploration across contexts and exploitation within each. In many modern applications, such tasks arise across multiple potentially heterogeneous but related clients, where collaboration can significantly improve learning efficiency. We propose CCBO, Collaborative Contextual Bayesian Optimization, a unified framework enabling multiple clients to jointly perform CBO with controllable contexts, supporting both online collaboration and offline initialization from peers' historical beliefs, with an optional privacy-preserving communication mechanism. We establish sublinear regret guarantees and demonstrate, through extensive simulations and a real-world hot rolling application, that CCBO achieves substantial improvements over existing approaches even under client heterogeneity. The code to reproduce the results can be found at https://github.com/cchihyu/Collaborative-Contextual-Bayesian-Optimization

  PublisherOA PDF

• Collaborative Contextual Bayesian Optimization

  arXiv (Cornell University) · 2026-04-20

  preprintOpen accessSenior author

  Discovering optimal designs through sequential data collection is essential in many real-world applications. While Bayesian Optimization (BO) has achieved remarkable success in this setting, growing attention has recently turned to context-specific optimal design, formalized as Contextual Bayesian Optimization (CBO). Unlike BO, CBO is inherently more challenging as it must approximate an entire mapping from the context space to its corresponding optimal design, requiring simultaneous exploration across contexts and exploitation within each. In many modern applications, such tasks arise across multiple potentially heterogeneous but related clients, where collaboration can significantly improve learning efficiency. We propose CCBO, Collaborative Contextual Bayesian Optimization, a unified framework enabling multiple clients to jointly perform CBO with controllable contexts, supporting both online collaboration and offline initialization from peers' historical beliefs, with an optional privacy-preserving communication mechanism. We establish sublinear regret guarantees and demonstrate, through extensive simulations and a real-world hot rolling application, that CCBO achieves substantial improvements over existing approaches even under client heterogeneity. The code to reproduce the results can be found at https://github.com/cchihyu/Collaborative-Contextual-Bayesian-Optimization

  PublisherDOI

• Language-Induced Priors for Domain Adaptation

  arXiv (Cornell University) · 2026-05-14

  preprintOpen accessSenior author

  Domain adaptation faces a fundamental paradox in the cold-start regime. When target data is scarce, statistical methods fail to distinguish relevant source domains from irrelevant ones, which often leads to negative transfer. In this paper, we address this challenge by leveraging expert textual descriptions of the target domain, a resource that is often available but overlooked. We propose a probabilistic framework that translates these semantic descriptions into a choice model, namely a Language-Induced Prior (LIP), that learns the preferences from a pretrained Large Language Model (LLM). The LIP is then integrated into an Expectation-Maximization algorithm to identify source relevance. Methodologically, this framework is compatible with any parametric model where a likelihood is available. It allows the LIP to guide the selection of sources when target signals are weak, while gradually refining these choices as samples accumulate. Theoretically, we prove that the estimator roughly matches an oracle cold-start MSE under a correct prior, while remaining asymptotically consistent regardless of the quality of the LIP. Empirically, we validated the framework on a descriptive (Gaussian estimation), a predictive (C-MAPSS dataset), and a prescriptive task (MuJoCo hopper).

  PublisherDOI

• Effect of Uncertainty-Aware AI Models on Pharmacists’ Reaction Time and Decision-Making in a Web-Based Mock Medication Verification Task: Randomized Controlled Trial

  JMIR Medical Informatics · 2025-03-08 · 5 citations

  articleOpen access

  Background: Artificial intelligence (AI)-based clinical decision support systems are increasingly used in health care. Uncertainty-aware AI presents the model's confidence in its decision alongside its prediction, whereas black-box AI only provides a prediction. Little is known about how this type of AI affects health care providers' work performance and reaction time. Objective: This study aimed to determine the effects of black-box and uncertainty-aware AI advice on pharmacist decision-making and reaction time. Methods: Recruitment emails were sent to pharmacists through professional listservs describing a web-based, crossover, randomized controlled trial. Participants were randomized to the black-box AI or uncertainty-aware AI condition in a 1:1 manner. Participants completed 100 mock verification tasks with AI help and 100 without AI help. The order of no help and AI help was randomized. Participants were exposed to correct and incorrect prescription fills, where the correct decision was to "accept" or "reject," respectively. AI help provided correct (79%) or incorrect (21%) advice. Reaction times, participant decisions, AI advice, and AI help type were recorded for each verification. Likelihood ratio tests compared means across the three categories of AI type for each level of AI correctness. Results: A total of 30 participants provided complete datasets. An equal number of participants were in each AI condition. Participants' decision-making performance and reaction times differed across the 3 conditions. Accurate AI recommendations resulted in the rejection of the incorrect drug 96.1% and 91.8% of the time for uncertainty-aware AI and black-box AI respectively, compared with 81.2% without AI help. Correctly dispensed medications were accepted at rates of 99.2% with black-box help, 94.1% with uncertainty-aware AI help, and 94.6% without AI help. Uncertainty-aware AI protected against bad AI advice to approve an incorrectly filled medication compared with black-box AI (83.3% vs 76.7%). When the AI recommended rejecting a correctly filled medication, pharmacists without AI help had a higher rate of correctly accepting the medication (94.6%) compared with uncertainty-aware AI help (86.2%) and black-box AI help (81.2%). Uncertainty-aware AI resulted in shorter reaction times than black-box AI and no AI help except in the scenario where "AI rejects the correct drug." Black-box AI did not lead to reduced reaction times compared with pharmacists acting alone. Conclusions: Pharmacists' performance and reaction times varied by AI type and AI accuracy. Overall, uncertainty-aware AI resulted in faster decision-making and acted as a safeguard against bad AI advice to approve a misfilled medication. Conversely, black-box AI had the longest reaction times, and user performance degraded in the presence of bad AI advice. However, uncertainty-aware AI could result in unnecessary double-checks, but it is preferred over false negative advice, where patients receive the wrong medication. These results highlight the importance of well-designed AI that addresses users' needs, enhances performance, and avoids overreliance on AI.

  PublisherDOI

• LLINBO: Trustworthy LLM-in-the-Loop Bayesian Optimization

  ArXiv.org · 2025-05-20

  preprintOpen accessSenior author

  Bayesian optimization (BO) is a sequential decision-making tool widely used for optimizing expensive black-box functions. Recently, Large Language Models (LLMs) have shown remarkable adaptability in low-data regimes, making them promising tools for black-box optimization by leveraging contextual knowledge to propose high-quality query points. However, relying solely on LLMs as optimization agents introduces risks due to their lack of explicit surrogate modeling and calibrated uncertainty, as well as their inherently opaque internal mechanisms. This structural opacity makes it difficult to characterize or control the exploration-exploitation trade-off, ultimately undermining theoretical tractability and reliability. To address this, we propose LLINBO: LLM-in-the-Loop BO, a hybrid framework for BO that combines LLMs with statistical surrogate experts (e.g., Gaussian Processes (GP)). The core philosophy is to leverage contextual reasoning strengths of LLMs for early exploration, while relying on principled statistical models to guide efficient exploitation. Specifically, we introduce three mechanisms that enable this collaboration and establish their theoretical guarantees. We end the paper with a real-life proof-of-concept in the context of 3D printing. The code to reproduce the results can be found at https://github.com/UMDataScienceLab/LLM-in-the-Loop-BO.

  PublisherOA PDFDOI

• FCOM: A Federated Collaborative Online Monitoring Framework via Representation Learning

  Proceedings of the AAAI Conference on Artificial Intelligence · 2025-04-11

  articleOpen access

  Monitoring a large population of dynamic processes with limited resources presents a significant challenge across various industrial sectors. This is due to 1) the inherent disparity between the available monitoring resources and the extensive number of processes to be monitored and 2) the unpredictable and heterogeneous dynamics inherent in the progression of these processes. Online learning approaches, commonly referred to as bandit methods, have demonstrated notable potential in addressing this issue by dynamically allocating resources and effectively balancing the exploitation of high-reward processes and the exploration of uncertain ones. However, most online learning algorithms are designed for 1) a centralized setting that requires data sharing across processes for accurate predictions or 2) a homogeneity assumption that estimates a single global model from decentralized data. To overcome these limitations and enable online learning in a heterogeneous population under a decentralized setting, we propose a federated collaborative online monitoring method. Our approach utilizes representation learning to capture the latent representative models within the population and introduces a novel federated collaborative UCB algorithm to estimate these models from sequentially observed decentralized data. This strategy facilitates informed monitoring of resource allocation. The efficacy of our method is demonstrated through theoretical analysis, simulation studies, and its application to decentralized cognitive degradation monitoring in Alzheimer’s disease.

  PublisherOA PDFDOI

• Diffusion-Based Surrogate Modeling and Multi-Fidelity Calibration

  IEEE Transactions on Automation Science and Engineering · 2025-01-01 · 5 citations

  articleSenior author

  Physics simulations have become fundamental tools to study myriad engineering systems. As physics simulations often involve simplifications, their outputs should be calibrated using real-world data. In this paper, we present a diffusion-based surrogate (DBS) that calibrates multi-fidelity physics simulations with diffusion generative processes. DBS categorizes multi-fidelity physics simulations into inexpensive and expensive simulations, depending on the computational costs. The inexpensive simulations, which can be obtained with low latency, directly inject contextual information into diffusion models. Furthermore, when results from expensive simulations are available, DBS refines the quality of generated samples via a guided diffusion process. This design circumvents the need for large amounts of expensive physics simulations to train denoising diffusion models, thus lending flexibility to practitioners. DBS builds on Bayesian probabilistic models and is equipped with a theoretical guarantee that provides upper bounds on the Wasserstein distance between the sample and underlying true distribution. The probabilistic nature of DBS also provides a convenient approach for uncertainty quantification in prediction. Our models excel in cases where physics simulations are imperfect and sometimes inaccessible. We use a numerical simulation in fluid dynamics and a case study in laser-based metal powder deposition additive manufacturing to demonstrate how DBS calibrates multi-fidelity physics simulations with observations to obtain surrogates with superior predictive performance.

  PublisherDOI

• Suicide risk estimation in bipolar disorder using N200 and P300 event-related potentials and machine learning: A pilot study

  Journal of Affective Disorders Reports · 2025-01-14 · 1 citations

  articleOpen access

  • ERP's untapped potential in suicide risk estimation in BD investigated. • N200/P300 ERPs from a response inhibition paradigm analyzed using ML. • ERP latency outperformed amplitude in suicide risk estimation for BD. • N200 latency models showed promise with high AUC (78.2–89.3 %). • Explainable AI revealed distinct ERP feature contributions Individuals with bipolar disorder (BD) face an elevated suicide risk. While machine learning (ML) has been used to estimate suicide risk in BD, early predictors like demographics, past attempts, and self-reports are limited by their inability to provide individualized risk estimation, overemphasis on past attempters, and susceptibility to personal biases, underscoring the need for effective, objective markers. Event-related potentials (ERPs), widely studied in suicide research, remain unexplored in ML applications for BD. This pilot study applies ML to N200 and P300 ERP components from a response inhibition paradigm to estimate suicide risk in BD. We collected N200 and P300 peak amplitude and latency data from 57 Type I BD individuals (22 attempters and 35 non-attempters). Our two-stage ML approach employed adaptive Lasso logistic regression for feature selection, followed by deep neural network (DNN) modeling for classification. For post-hoc analysis, we used explainable AI to interpret ERP feature importance in top-performing DNN predictions. Key features were exclusively identified from latency data. Notably, N200 latency DNN models effectively distinguished attempters from non-attempters, achieving AUCs of 78.2–89.3 %. Explainable AI pinpointed a right visual hemifield Go stimuli-induced ERP from the left-parietal site as the most predictive. Our ERP-ML approach showed promising preliminary results, with N200 latency identified as a potential suicide marker in BD. Larger samples are required to validate these results. While findings are sample-specific, the methodological approach may have broader applicability and could inform future research to refine clinical strategies for detecting high-risk BD individuals.

  PublisherDOI

Recent grants

• CAREER: From the Cloud to the Crowd: An Enabling Solution for the Internet of Federated Things

  NSF · $500k · 2022–2027

Frequent coauthors

• Xubo Yue

  26 shared

• Naichen Shi

  University of Michigan–Ann Arbor

  16 shared

• Seokhyun Chung

  14 shared

• Qiyuan Chen

  University of Michigan–Ann Arbor

  12 shared

• Corey A. Lester

  University of Michigan–Ann Arbor

  11 shared

• X. Jessie Yang

  11 shared

• Shiyu Zhou

  10 shared

• Maher Nouiehed

  American University of Beirut

  9 shared

Education

• PhD, Industrial & Systems Engineering

  University of Wisconsin-Madison

  2018

• MS, Statistics

  University of Wisconsin–Madison

  2017

• BE, Civil & Environmental Engineering (Math Minor)

  American University of Beirut

  2014

Awards & honors

• IISE Transactions Service Award (2024)
• NSF CAREER Award (2022)
• Best Refereed Paper Recognition, Quality, Statistics & Relia…
• Featured Article in the December 2023 Issue of the Industria…
• Best Paper Recognition, Data Mining (DM) section, INFORMS An…