Reproduce “Robust Sampling in Deep Learning” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Aurora Cobo Aguilera, Antonio Artés-Rodríguez, Fernando Pérez-Cruz, Pablo Martínez Olmos

The authors introduce a minibatch sampling method for image classifiers trained with limited labeled data. It uses cross-entropy losses from the previous batch to repeat high-loss examples in the next. On CIFAR-10 with 5,000 training examples, VR-M-15 reaches 76.520% validation accuracy versus 69.360% for the baseline; gains are not statistically significant overall and are not consistent across settings.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.