2 citations · 3 across the 3 of their papers we have counts for
3 papers
cs.LG2021★ 1 cited
GABO: Graph Augmentations with Bi-level Optimization
Heejung W. Chung, Avoy Datta, Chris Waites
Data augmentation refers to a wide range of techniques for improving model generalization by augmenting training examples. Oftentimes such methods require domain knowledge about th…
cs.LG2021
Binarized Neural Networks for Resource-Constrained On-Device Gait Identification
Daniel J. Wu, Avoy Datta, Vinay Prabhu
User authentication through gait analysis is a promising application of discriminative neural networks -- particularly due to the ubiquity of the primary sources of gait accelerome…
cs.LG2021★ 2 cited
Continuous Weight Balancing
Daniel J. Wu, Avoy Datta
We propose a simple method by which to choose sample weights for problems with highly imbalanced or skewed traits. Rather than naively discretizing regression labels to find binned…