ChainzRule uses learnable polynomial layers with differential regularization on the Jacobian to promote stable low-frequency representations, claiming improved sample efficiency and robustness on multiple benchmarks.
Fine-grained sentiment classification using BERT.arXiv preprint arXiv:1910.03474, 2019.https://arxiv.org/abs/1910.03474
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
CR networks maintain accuracy advantages and near-unit gradient tail ratios over ReLU baselines from 5% to 100% training data on Pima Diabetes and SST-5, with the gradient tail ratio proposed as a label-free generalization diagnostic.
citing papers explorer
-
ChainzRule: Sample-Efficient, Robust Deep Learning Across Tabular, NLP, and Vision Tasks
ChainzRule uses learnable polynomial layers with differential regularization on the Jacobian to promote stable low-frequency representations, claiming improved sample efficiency and robustness on multiple benchmarks.
-
Layer-wise Derivative Controlled Networks Achieve Competitive Accuracy and Gradient Stability Across Data Regimes
CR networks maintain accuracy advantages and near-unit gradient tail ratios over ReLU baselines from 5% to 100% training data on Pima Diabetes and SST-5, with the gradient tail ratio proposed as a label-free generalization diagnostic.