Ensuring alignment, which refers to making models behave in accordance with human
intentions [1, 2], has become a critical task before deploying large language models (LLMs) …

Recent work has shown that offline reinforcement learning (RL) can be formulated as a
sequence modeling problem (Chen et al., 2021; Janner et al., 2021) and solved via …

In performative prediction, predictions guide decision-making and hence can influence the
distribution of future data. To date, work on performative prediction has focused on finding …

We introduce the notion of performative power, which measures the ability of a firm
operating an algorithmic system, such as a digital content recommendation platform, to …

Predictions about people, such as their expected educational achievement or their credit
risk, can be performative and shape the outcome that they are designed to predict …

Performative distribution shift captures the setting where the choice of which ML model is
deployed changes the data distribution. For example, a bank which uses the number of …

Stochastic optimization problems often involve data distributions that change in reaction to
the decision variables. This is the case, for example, when members of the population …

Deployed supervised machine learning models make predictions that interact with and
influence the world. This phenomenon is called performative prediction by Perdomo et …

Learning problems commonly exhibit an interesting feedback mechanism wherein the
population data reacts to competing decision makers' actions. This paper formulates a new …

When reasoning about strategic behavior in a machine learning context it is tempting to
combine standard microfoundations of rational agents with the statistical decision theory …