Sparse ridge regression problems play a significant role across various domains.

Existing solutions either work under very specific assumptions or achieve bounds that are vacuous in some regimes.

In reinforcement learning (RL), a recurring goal is to find a diverse set of high-valued state-action trajectories according to a reward function.

Panacea trains a single model capable of adapting online and Pareto-optimally to diverse sets of preferences without the need for further tuning.

Concretely, we prove that polynomial-sized message-passing GNN's can learn the

We study a class of optimization problems motivated by automating the design and update of AI systems like coding assistants, robots, and copilots.