Dataset Distillation and Coreset Selection

Dataset Distillation and Coreset Selection are techniques for compressing large-scale datasets into smaller, more manageable forms while preserving the essential information needed for model training. Dataset Distillation synthesizes a compact set of representative samples that encapsulate the knowledge of the full dataset, whereas Coreset Selection identifies and retains the most informative subset from the original data. Both approaches aim to reduce storage and computational costs without significantly sacrificing model performance.