Gradient-based dataset distillation of two-layer ReLU nets on multi-index models encodes the r-dimensional principal subspace into synthetic data of memory complexity Θ̃(r²d+L) that recovers high generalization.
Provable and efficient dataset distillation for kernel ridge regression
1 Pith paper cite this work, alongside 2 external citations. Polarity classification is still indexing.
1
Pith paper citing it
2
external citations · OpenAlex
fields
cs.LG 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Dataset Distillation Efficiently Encodes Low-Dimensional Representations from Gradient-Based Learning of Non-Linear Tasks
Gradient-based dataset distillation of two-layer ReLU nets on multi-index models encodes the r-dimensional principal subspace into synthetic data of memory complexity Θ̃(r²d+L) that recovers high generalization.