TaskMet: Task-driven Metric Learning for Model Learning

Dishank Bansal, Ricky T. Q. Chen, Mustafa Mukadam, Brandon Amos

Keywords: task-based learning, decision-focused learning

TL;DR: Using task loss to learn parameterized prediction loss, which are then used to train prediction models

Abstract: Deep learning models are often used with some downstream task. Models solely trained to achieve accurate predictions may struggle to perform well on the desired downstream tasks. We propose using the task loss to learn a metric which parameterizes a loss to train the model. This approach does not alter the optimal prediction model itself, but rather changes the model learning to emphasize the information important for the downstream task. This enables us to achieve the best of both worlds: a prediction model trained in the original prediction space while also being valuable for the desired downstream task. We validate our approach through experiments conducted in two main settings: 1) decision-focused model learning scenarios involving portfolio optimization and budget allocation, and 2) reinforcement learning in noisy environments with distracting states.

Submission Number: 5186