Search Results for author:
Found 5 papers, 0 papers with code
fAux: Testing Individual Fairness via Gradient Alignment
We propose a novel criterion for evaluating individual fairness and develop a practical testing method based on this criterion which we call fAux (pronounced fox).
Nonlocal optimization of binary neural networks
We explore training Binary Neural Networks (BNNs) as a discrete variable inference problem over a factor graph.
Scalable Whitebox Attacks on Tree-based Models
Adversarial robustness is one of the essential safety criteria for guaranteeing the reliability of machine learning models.
Parity Partition Coding for Sharp Multi-Label Classification
The problem of efficiently training and evaluating image classifiers that can distinguish between a large number of object categories is considered.
On Learning Wire-Length Efficient Neural Networks
Pruning neural networks for wiring length efficiency is considered.
