KAMA-NNs: Low-dimensional Rotation Based Neural Networks

By Krzysztof Marcin Choromanski, Aldo Pacchiano, Jeffrey Pennington, Yunhao Tang. 2019

6 citations recorded by the source corpus.

Subfields: Model Architectures, Efficiency & Compression

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Model Architectures

1. Adrian Weller
2. Valerii Likhosherstov
3. Jared Davis
4. Xingyou Song
5. Krzysztof Marcin Choromanski
6. Tamás Sarlós
7. David Belanger
8. Lucy J. Colwell

In Efficiency & Compression

1. Adrian Weller
2. Krzysztof Marcin Choromanski
3. Jared Davis
4. Xingyou Song
5. Valerii Likhosherstov

Citations in the corpus

• Masked Language Modeling for Proteins via Linearly Scalable Long-Context Transformers (2020, methodology): “ORFs were introduced to reduce the variance of Monte Carlo estimators [56, 13, 12, 10, 41, 9, 11] and we show in Secs.”
• Demystifying Orthogonal Monte Carlo and Beyond (2020, background): “First Strong Results for Classes of PNG Kernels: We also obtain first exponentially small upper bounds on errors for OMCs applied to PNG kernels, which were previously intractable and for which the best known results were coming from second moment methods [18, 13].”