Alexandra (Ola) Zytek
Machine learning algorithms are becoming increasingly powerful - but how can we extend their benefits to a diverse set of real-world domains? Models continue to be black-boxes that confuse and concern users, and applying them can be a difficult and complicated process.
My research aims to bridge the gap between algorithms and real-world users through collaborations with end-users and development of software systems and interfaces that make applying ML with seamless support for the nuances of real-world domains easier.
I am a PhD student at MIT, researching at the Data to AI lab under the supervision of Kalyan Veeramachaneni.
Zytek, A., Arnaldo, I., Liu, D., Berti-Equille, L., & Veeramachaneni, K. (2022). The Need for Interpretable Features: Motivation and Taxonomy. arXiv preprint arXiv:2202.11748.
Liu, D., Alnegheimish, S., Zytek, A., & Veeramachaneni, K. (2021). MTV: Visual Analytics for Detecting, Investigating, and Annotating Anomalies in Multivariate Time Series. arXiv preprint arXiv:2112.05734.
Zytek, A., Liu, D., Vaithianathan, R., & Veeramachaneni, K. (2021). Sibyl: Understanding and Addressing the Usability Challenges of Machine Learning In High-Stakes Decision Making. In IEEE Transactions on Visualization and Computer Graphics (VIS).
Cheng, F., Liu, D., Du, F., Lin, Y., Zytek, A., Li, H., Qu, H. & Veeramachaneni, K. (2021). VBridge: Connecting the Dots Between Features, Explanations, and Data for Healthcare Models. In IEEE Transactions on Visualization and Computer Graphics (VIS). Honorable Mention.
Zytek, A., Liu, D., Vaithianathan, R., & Veeramachaneni, K. (2021, May). Sibyl: Explaining Machine Learning Models for High-Stakes Decision Making. In Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems (pp. 1-6).
McGrath, S., Mehta, P., Zytek, A., Lage, I., & Lakkaraju, H. (2020). When Does Uncertainty Matter?: Understanding the Impact of Predictive Uncertainty in ML Assisted Decision Making. arXiv preprint arXiv:2011.06167.
Paul, S., Hole, F., Zytek, A., & Varela, C. A. (2018, September). Wind-aware trajectory planning for fixed-wing aircraft in loss of thrust emergencies. In 2018 IEEE/AIAA 37th Digital Avionics Systems Conference (DASC) (pp. 1-10). IEEE.
Paul, S., Hole, F., Zytek, A., & Varela, C. A. (2017). Flight trajectory planning for fixed-wing aircraft in loss of thrust emergencies. In the Second International Conference on InfoSymbiotics (DDDAS).
Zytek, A. (2021). Towards Usable Machine Learning (S.M. thesis, MIT).
Project Website: https://sibyl-ml.dev/
A python library that provides ML usability tools and explanations that are designed for use by human decision-makers.
API for developing ML usability tools.
User interface for a usable ML decision aid for child welfare screening.
zyteka at mit dot edu
MIT Stata Center
32 Vassar St, Room 32-D712
Cambridge, MA 02139