LGAINEMLOct 21, 2022

Efficient Dataset Distillation Using Random Feature Approximation

arXiv:2210.12067v1145 citationsh-index: 26
Originality Incremental advance
AI Analysis

This incremental improvement addresses the storage and computational burden for researchers and practitioners using dataset distillation, enabling faster processing on standard hardware.

The paper tackles the computational inefficiency of the state-of-the-art dataset distillation method KIP by proposing a random feature approximation algorithm, achieving at least a 100-fold speedup while maintaining competitive accuracy across large-scale datasets.

Dataset distillation compresses large datasets into smaller synthetic coresets which retain performance with the aim of reducing the storage and computational burden of processing the entire dataset. Today's best-performing algorithm, \textit{Kernel Inducing Points} (KIP), which makes use of the correspondence between infinite-width neural networks and kernel-ridge regression, is prohibitively slow due to the exact computation of the neural tangent kernel matrix, scaling $O(|S|^2)$, with $|S|$ being the coreset size. To improve this, we propose a novel algorithm that uses a random feature approximation (RFA) of the Neural Network Gaussian Process (NNGP) kernel, which reduces the kernel matrix computation to $O(|S|)$. Our algorithm provides at least a 100-fold speedup over KIP and can run on a single GPU. Our new method, termed an RFA Distillation (RFAD), performs competitively with KIP and other dataset condensation algorithms in accuracy over a range of large-scale datasets, both in kernel regression and finite-width network training. We demonstrate the effectiveness of our approach on tasks involving model interpretability and privacy preservation.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes