Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

count% of corpus
0.3%0.5%0.8%0.1% · Jan 202019922001200920172026
1 result for “batchboost”
batchboost: regularization for stabilizing training with resistance to underfitting & overfittingcs.LG

Batchboost stabilizes training by mixing and pairing samples, improving accuracy.

problem Stabilizing training in machine learning, especially avoiding overfitting and underfitting.
method Batchboost pipeline with three stages: pairing, mixing, and feeding. Mixing uses mixup technique.
result Batchboost achieves 0.5-3% better accuracy than mixup on CIFAR-10 & Fashion-MNIST.
batchboostmixingpairingstabilizationtraining
2020-01-21abs ↗pdf ↗