Teaching and Research Interests: In my research, I am interested in developing interactive optimization methods to train machine learning models to operate in sociotechnical contexts. As a teacher and mentor, I am excited about creating learning experiences that are accessible, and that emphasize both technical computer science skills and skills for understanding and communicating the implications of computing systems.
Experience: I am an Assistant Professor of Computer Science at Colby College since July 2023. I completed my Ph.D. in Computer Science at Harvard with Professor Finale Doshi-Velez, where my work was supported by an NSF GRFP fellowship. I completed an internship at Microsoft Research in Summer 2020 in the Adaptive Systems and Interaction Group where I was supervised by Dr. Ece Kamar. Before starting my PhD, I worked with Professor David Sontag as a Research Software Engineer at MIT and NYU. I earned a B.A. in Computer Science and Social & Cultural Analysis from NYU in 2016.
Service and Outreach: I participated in the development and analysis of the initial Harvard SEAS (School of Engineering and Applied Sciences) Climate Survey as a member of the SEAS Diversity, Inclusion and Belonging committee. I have also participated as a mentor in several programs aimed at students from underrepresented groups in STEM including the Try-AI mentoring program and the Women in Data Science Cambridge workshop.
Other Interests: Outside of my academic life, I like to make pottery and hang out with my cat Billie Jean.
Teaching Experience:
- Lecture and lab instructor for CS 152–Computational Thinking: Science at Colby in FA23, SP24, FA24
- Lab instructor for CS 231–Data Structures and Algorithms at Colby in FA23 SP24, SP25
- Lecture instructor for CS 348-Human-Centered Machine Learning in FA24
- Lecture instructor for CS 348-Human-Centered Machine Learning II in SP25
- Teaching Certificate through the Derek Bok Center for Teaching and Learning at Harvard, Spring 2023
- Pedagogy Fellow for Harvard SEAS (School of Engineering and Applied Sciences) in AY 2022-2023
- Instructor for Statistical Pattern Recognition at Tufts in Spring 2022
- Teaching Fellow (TA) for Interpretability and Explainability in Machine Learning at Harvard in Fall 2019
- Teaching Fellow (TA) for Advanced Machine Learning at Harvard in Fall 2018
Publications:
- Li, Y., Lefebvre, L., Parbhoo, S., Doshi-Velez, F., Lage, I. User Studies in Human-Feature-Integration. IUI Workshop on Adaptive XAI. 2025.
- Lage, I., Parbhoo, S., & Doshi-Velez, F. Towards Integrating Personal Knowledge into Test-Time Predictions. arXiv preprint. 2024
- McGrath, S.*, Mehta, P.*, Zytek, A., Lage, I., Lakkaraju, H. When does uncertainty matter?: Understanding the impact of predictive uncertainty in ML assisted decision making. Transactions on Machine Learning Research. 2023.
- Lage, I., McCoy, T. H., Perlis, R. H., Doshi-Velez F. Efficiently identifying individuals at high risk for treatment resistance in major depressive disorder using electronic health records. Journal of Affective Disorders Volume 306. 2022.(Editor's choice article)
- Narayanan, S., Lage, I. & Doshi-Velez, F. (When) Are Contrastive Ex- planations of Reinforcement Learning Policies Useful?. NeurIPS Workshop on Human in the Loop Learning. 2022.
- Lage, I., Pradier, M. F., McCoy, T. H., Perlis, R. H., Doshi-Velez F. Do clinicians follow heuristics in prescribing antidepressants? Journal of Affective Disorders Volume 311. 2022.
- Mahinpei, A.*, Clark, J.*, Lage, I., Doshi-Velez, F., Pan, W., Promises and Pitfalls of Black-Box Concept Learning Models. ICML: Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI. 2021. (Mentoring role)
- Lage, I., Doshi-Velez, F. Learning interpretable concept-based models with human feedback. ArXiv Pre-print. 2020.
- Tabac A., Wigell, R., Wolf, K., Lage, I., Landrum, S., Reyes Nieva, H., Bearnot B., Streed, C. Using Patterns of Missing EHR Data to Identify Care Disparities in Gender Diverse Patients. Abstract at American Public Health Association. 2020.
- Lage I*, Chen E*, He J*, Narayanan M*, Gershman S, Kim B, Doshi-Velez F. Human Evaluation of Models Built for Interpretability. AAAI Conference on Human Computation and Crowdsourcing (HCOMP). 2019. (Honorable mention for best paper)
- Lage I*, Lifschitz D*, Doshi-Velez F, Amir O. Exploring Computational User Models for Agent Policy Summarization. International Joint Conference on Artificial Intelligence (IJCAI). 2019.
- Lage I, Lifschitz D, Doshi-Velez F, Amir O. Toward Robust Policy Summarization--Extended Abstract. International conference on Autonomous Agents and Multi-Agent Systems (AAMAS). 2019.
- Lage I, Ross A, Kim B, Gershman S, Doshi-Velez F. Human-in-the-Loop Interpretability Prior. Conference on Neural Information Processing Systems (NeurIPS). 2018. (Selected for spotlight--3.5\% of submitted papers)
- Ross AS*, Lage I*, Doshi-Velez F. The Neural Lasso: Local Linear Sparsity for Interpretable Explanations. Neural Information Processing Systems (NIPS) Workshop on Transparent and Interpretable Machine Learning in Safety Critical Environments. 2017.