Scaling noise magnitude in NCE aligns gradients with MLE, enabling a practical approximation that improves performance on CIFAR-10 and ImageNet image modeling with fewer training steps.
BOOTGEN (Kim et al., 2024) focuses specifcially on optimizing biological sequences
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
"Noisier" Noise Contrastive Eestimation is (Almost) Maximum Likelihood
Scaling noise magnitude in NCE aligns gradients with MLE, enabling a practical approximation that improves performance on CIFAR-10 and ImageNet image modeling with fewer training steps.