The Lyra research project is a long-term research effort to enhance the understanding and reliabilty of data science software. It aims ad developing new practical and accessible analyses and tools to reason about and provide rigorous guarantees of the behavior of data analytics, big data, machine learning, and deep learning applications.
Lyra is an umbrella project including the following focused research projects:
Libra (focused on fairness-aware training and certification of machine learning models)
Sedano (focused on designing and developing static analyses for data science notebooks)
Completed Projects
- Abhinandan Pal (Bachelor Student, IIIT Kalyani, India)
Abstract Interpretation-based Feature Ranking for SVMs
Research Internship (remote), 2022 - Serge Durand
Static Analysis by Abstract Interpretation of the ACAS Xu Neural Networks
M1 Internship, École Normale Supérieure, 2020 - Radwa Sherif Abdelbar
Automated Checking of Implicit Assumptions on Textual Data
Bachelor’s Thesis, ETH Zurich, SS 2018 - Lowis Engel
Usage Analysis of Data Stored in Map Data Structures
Bachelor’s Thesis, ETH Zurich, SS 2018 - Madelin Schumacher
Automated Generation of Data Quality Checks
Master’s Thesis, ETH Zurich, AS 2017 - Mostafa Hassan
Static Type Inference for Python
Bachelor’s Thesis, ETH Zurich, SS 2017 - Simon Wehrli
Static Program Analysis of Data Usage Properties
Master’s Thesis, ETH Zurich, SS 2017