most citedScalable and Efficient Training of Large Convolutional Neural Networks with Differential Privacy

8 citations · 8 across the 2 of their papers we have counts for

collaborators

2 papers

cs.LG2022★ 8 cited

Scalable and Efficient Training of Large Convolutional Neural Networks with Differential Privacy

Zhiqi Bu, Jialin Mao, Shiyun Xu

Large convolutional neural networks (CNN) can be difficult to train in the differentially private (DP) regime, since the optimization algorithms require a computationally expensive…

stat.ML2022

Sparse Neural Additive Model: Interpretable Deep Learning with Feature Selection via Group Sparsity

Shiyun Xu, Zhiqi Bu, Pratik Chaudhari +1

Interpretable machine learning has demonstrated impressive performance while preserving explainability. In particular, neural additive models (NAM) offer the interpretability to th…