Events
Colloquium
What Makes Treatment Effects Identifiable? Characterizations and Estimators Beyond Unconfoundedness
 |
Speaker: Anay Mehrotra (Yale) Ph.D. Candidate Yale University Wednesday, September 10, 2025 11:30AM - 1:00PM Lunch will be service in 1307 at 11:30am
Talk will be 12:00-1:00pm in 1327 Location: Yale Institute for Foundations of Data Science, Kline Tower 13th Floor, Room 1327, New Haven, CT 06511 and via Webcast: https://yale.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=bf5b6eee-4f90-4a3f-87d5-b34e01176ac2 |
Talk summary: Sometimes, like when studying the effects of smoking, it is impossible to run a randomized control trial and we must rely on observational data—where we observe who chose to receive treatment but do not control the assignment of the treatment. This leads to a fundamental challenge: we only see one outcome per individual (their health either as a smoker or non-smoker, but never both), making it impossible to directly observe causal effects. Unlike typical machine learning tasks where given enough data and computational power learning is always possible, causal inference requires assumptions to enable learning. Unfortunately, these assumptions frequently fail—severely limiting when causal effects can be identified.
In this talk, I will present a characterization of when treatment effects are identifiable from observational data, which unifies existing approaches and enables exact identification of treatment effects in scenarios where current methods only provide approximate bounds. I will explain how these scenarios capture classical models such as special cases of sensitivity analysis and regression discontinuity designs. The characterization we present bridges causal inference with classical learning theory and opens exciting new avenues for causal estimation when standard assumptions fail.
This talk is based on joint work with Yang Cai, Alkis Kalavasis, Katerina Mamali, and Manolis Zampetakis.
Speaker bio: Anay Mehrotra is a PhD candidate at Yale University advised by Amin Karbasi and Manolis Zampetakis. His research applies learning-theoretic tools to missing-data challenges (ranging from causal inference and truncated statistics to omissions driven by societal biases). He leverages these insights to assess the potential and limitations of modern AI systems, often contributing novel tools back into learning theory. His work has received the Best Paper Award at COLT, been featured in the WIRED, and received the Sir Binay Kumar Sinha award from IIT Kanpur.
Add To: Google Calendar | Outlook | iCal File
- Colloquium
Submit an Event
Interested in creating your own event, or have an event to share? Please fill the form if you’d like to send us an event you’d like to have added to the calendar.