The reviewed record of science sign in
Pith

arxiv: 2311.13583 · v1 · pith:UJS7CDBI · submitted 2023-11-22 · cs.LG

Adaptive Sampling for Deep Learning via Efficient Nonparametric Proxies

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:UJS7CDBIrecord.jsonopen to challenge →

classification cs.LG
keywords samplingeffectiveneuralnonparametricscorestrainingalgorithmscomputationally
0
0 comments X
read the original abstract

Data sampling is an effective method to improve the training speed of neural networks, with recent results demonstrating that it can even break the neural scaling laws. These results critically rely on high-quality scores to estimate the importance of an input to the network. We observe that there are two dominant strategies: static sampling, where the scores are determined before training, and dynamic sampling, where the scores can depend on the model weights. Static algorithms are computationally inexpensive but less effective than their dynamic counterparts, which can cause end-to-end slowdown due to their need to explicitly compute losses. To address this problem, we propose a novel sampling distribution based on nonparametric kernel regression that learns an effective importance score as the neural network trains. However, nonparametric regression models are too computationally expensive to accelerate end-to-end training. Therefore, we develop an efficient sketch-based approximation to the Nadaraya-Watson estimator. Using recent techniques from high-dimensional statistics and randomized algorithms, we prove that our Nadaraya-Watson sketch approximates the estimator with exponential convergence guarantees. Our sampling algorithm outperforms the baseline in terms of wall-clock time and accuracy on four datasets.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Entropy as a Structural Prior: How a Log-Barrier on DiT Belief Space Drives Musical Diversity and Development

    cs.SD 2026-06 unverdicted novelty 7.0

    An entropy-based log-barrier on DiT outputs acts as an online curriculum in supervised diffusion fine-tuning, producing higher thematic development and textural diversity than standard training on MusicCaps.