I am a PhD student in the Human-Computer Interaction Institute (HCII) within the School of Computer Science at Carnegie Mellon University. I am fortunate to be advised by Steven Wu and Ken Holstein.

My work examines the reliability and validity of data-driven algorithms deployed in high-stakes decision-making settings. I develop algorithmic methods and evaluation tools to help practitioners assess the feasibility of model deployments given real-world complexities. I adopt an interdisciplinary approach, leveraging methods from HCI, machine learning, and causal inference. My work is generously supported by an NSF Graduate Research Fellowship and the Center for Advancing Safety of Machine Intelligence (CASMI).

Previously, I completed my Master’s in Computer Science at Cambridge. I also studied Computer Science and Psychology at the University of Missouri, where I co-founded TigerAware, a mobile-based research platform.

Luke Guerdan
lguerdan [at] cs.cmu.edu

News & Travel

Feb 2024 I will give an invited talk “Human-Algorithm Decision-Making Under Imperfect Proxy Labels” at the 2024 Lecture Series on Network Inequality at CSH Vienna.
Dec 2023 I will present ongoing work at the NeurIPS Regulatable ML Workshop on Saturday December 16th.
Jun 2023 Our work Counterfactual Prediction Under Outcome Measurement Error won a Best Paper Award at FAccT 23’.
Apr 2023 Two papers accepted at FAccT 23’.

Conference Papers

  1. Training Towards Critical Use: Learning to Situate AI Predictions Relative to Human Knowledge Anna Kawakami, Luke Guerdan, Yanghuidi Cheng, Kate Glazko, Matthew Lee, Scott Carter, Nikos Arechiga, Haiyi Zhu, and Kenneth Holstein Proceedings of The ACM Collective Intelligence Conference, 2023
  2. Counterfactual Prediction Under Outcome Measurement Error Luke Guerdan, Amanda Coston, Kenneth Holstein, and Steven Wu Proceedings of the ACM Conference on Fairness, Accountability, and Transparency (FAccT), 2023 [PDF] [Video] [Code]
  3. Ground(less) Truth: A Causal Framework for Proxy Labels in Human-Algorithm Decision-Making Luke Guerdan, Amanda Coston, Steven Wu, and Kenneth Holstein Proceedings of the ACM Conference on Fairness, Accountability, and Transparency (FAccT), 2023 [PDF] [Video]
  4. Federated Continual Learning for Socially Aware Robotics Luke Guerdan, and Hatice Gunes Proceedings of the 32nd IEEE International Conference on Robot & Human Interactive Communication (RO-MAN), 2023 [PDF]
  5. Extracting Motion-Related Subspaces from EEG in Mobile Brain/Body Imaging Studies Lukas Gehrke*, Luke Guerdan*, and Klaus Gramman 9th International IEEE/EMBS Conference on Neural Engineering, 2019 [PDF] [Poster]
  6. TigerAware: An Innovative Mobile Survey and Sensor Data Collection and Analytics System Will Morrison, Luke Guerdan, Jayanth Kanugo, Tim Trull, and Yi Shang IEEE DSC, 2018
  7. Augmented Resource Allocation Framework for Disaster Response Coordination in Mobile Cloud Environments Luke Guerdan, Olivia Apperson, and Prasad Calyam IEEE MobileCloud, 2017 [PDF] [Poster]
  8. ADA - Automatic Detection of Alcohol Usage for Mobile Ambulatory Assessment Peng Sun, Nick Wergeles, Cheng Zhang, Luke Guerdan, Tim Trull, and Yi Shang IEEE SmartComp, 2016

Workshops & Preprints

  1. Policy Comparison Under Unmeasured Confounding Luke Guerdan, Amanda Coston, Kenneth Holstein*, and Steven Wu* NeurIPS 2023 Workshop on Regulatable ML (RegML), 2023
  2. Ground(less) Truth: The Problem with Proxy Outcomes in Human-AI Decision-Making Luke Guerdan, Amanda Coston, Ken Holstein, and Steven Zhiwei Wu NeurIPS 2022 Workshop on Human-Centered AI (HCAI), 2022
  3. Counterfactual Decision Support Under Treatment-Conditional Outcome Measurement Error Luke Guerdan, Amanda Coston, Ken Holstein, and Steven Zhiwei Wu NeurIPS 2022 Workshop on Causality for Real-world Impact, 2022
  4. Under-reliance or misalignment? How Proxy Outcomes Limit Measurement of Appropriate Reliance in AI-assisted Decision-Making Luke Guerdan, Kenneth Holstein, and Steven Wu ACM CHI 2022 Workshop on Trust and Reliance in AI-Human Teams (TRAIT), 2022 [PDF] [Video]
  5. Under-reliance or misalignment? How Proxy Outcomes Limit Measurement of Appropriate Reliance in AI-assisted Decision-Making Luke Guerdan, Kenneth Holstein, and Steven Wu ACM CHI 2022 Workshop on Trust and Reliance in AI-Human Teams (TRAIT), 2022 [PDF] [Video]
  6. Towards a Learner-Centered Explainable AI Anna Kawakami, Luke Guerdan, Yang Cheng, Anita Sun, Alison Hu, Kate Glazko, Nikos Arechiga, Matthew Lee, Scott Carter, Haiyi Zhu, and Kenneth Holstein ACM CHI 2022 Workshop on Human-Centered Explainable AI (HCXAI), 2022 [PDF]
  7. Toward Affective XAI: Facial Affect Analysis for Understanding Explainable Human-AI Interactions Luke Guerdan, Alex Raymond, and Hatice Gunes ICCV Workshop on Responsible Pattern Recognition and Machine Intelligence, 2021 [PDF] [Video]
  8. Deep Learning vs. Classical Machine Learning: A Comparison of Methods for Fluid Intelligence Prediction Luke Guerdan*, Peng Sun*, Connor Rowland, Logan Harrison, Zhang Tang, Nick Wergeles, and Yi Shang MICCAI Adolescent Brain Cognitive Development Neurocognitive Prediction Challenge, 2019 [PDF]