Views Navigation

Event Views Navigation

Latest Past Events

Fundamental statistical limits in causal inference

E18-304

Abstract: Despite tremendous methodological advances in causal inference, there remain significant gaps in our understanding of the fundamental statistical limits of estimating various causal estimands from observational data. In this talk I will survey some recent work that aims to make some progress towards closing these gaps. Particularly, I will discuss the fundamental limits of estimating various important causal estimands under classical smoothness assumptions, under new "structure-agnostic" assumptions, in a discrete setup, and under partial smoothness assumptions. Via these fundamental…

Calibrated Mechanism Design

MIT Building E18, Room 304 Ford Building (E18), 50 Ames Street, Cambridge

Abstract:  We study optimal mechanism design in settings where a designer has private information and interacts repeatedly with strategic agents. Motivated by applications like ad auctions, we introduce calibrated mechanism design, in which mechanisms must be robust to the information agents learn over time through participation. We formalize this via calibrated information structures, capturing what players infer from repeated interaction. We characterize implementable outcomes under this constraint, provide a decomposition result in single-agent environments, and show that learning endogenous to…

Tractable Agreement Protocols

E18-304

Abstract: As ML models become increasingly powerful, it is an attractive proposition to use them in important decision making pipelines, in collaboration with human decision makers. But how should a human being and a machine learning model collaborate to reach decisions that are better than either of them could achieve on their own? If the human and the ML model were perfect Bayesians, operating in a setting with a commonly known and correctly specified prior, Aumann's classical agreement theorem would give us…


MIT Institute for Data, Systems, and Society
Massachusetts Institute of Technology
77 Massachusetts Avenue
Cambridge, MA 02139-4307
617-253-1764