Dataset distillation can be formulated as a bi-level meta-learning problem where the outer loop optimizes the metadataset and the inner loop trains a model on the distilled data.

The above problem requires the knowledge of the distributionπ which is typically unknown in practice.

Therefore, they seemtobegoodcandidatestobuild SSPsolutions, since Property 1 statesthattheidealsolverU is permutation-equivariant (thiswillbeconfirmedby Corollary 1).

Large language models (LLMs) have been increasingly used to interact with external environments (e.g., games, compilers, APIs) as goal-driven agents.

Foundation models [6] such as CLIP [47] have been extensively utilized on diverse domains via pretrain-finetune approaches.

The goal is to find the global optimal arm, and agents are able to pull any arm; however, they can only observe the reward when the selected arm is local.