Online Convex Optimization Perspective for Learning from Dynamically Revealed Preferences
This work addresses the challenge of online learning from revealed preferences for applications in economics and machine learning, representing an incremental improvement with a unified framework.
The paper tackles the problem of learning an agent's utility function from observed actions in a changing environment by introducing a new convex loss function within an online convex optimization framework, achieving improved regret performance and solution time compared to existing methods.
We study the problem of online learning (OL) from revealed preferences: a learner wishes to learn a non-strategic agent's private utility function through observing the agent's utility-maximizing actions in a changing environment. We adopt an online inverse optimization setup, where the learner observes a stream of agent's actions in an online fashion and the learning performance is measured by regret associated with a loss function. We first characterize a special but broad class of agent's utility functions, then utilize this structure in designing a new convex loss function. We establish that the regret with respect to our new loss function also bounds the regret with respect to all other usual loss functions in the literature. This allows us to design a flexible OL framework that enables a unified treatment of loss functions and supports a variety of online convex optimization algorithms. We demonstrate with theoretical and empirical evidence that our framework based on the new loss function (in particular online Mirror Descent) has significant advantages in terms of regret performance and solution time over other OL algorithms from the literature and bypasses the previous technical assumptions as well.