资源分类
》 资源 》论文》Nearly-Optimal Private LASSO

Nearly-Optimal Private LASSO

2020-02-07 | |  58 |   40 |   0

Abstract 

We present a nearly optimal differentially private version of the well known LASSO estimator. Our algorithm provides privacy protection with respect to each training example. The excess risk of our algorithm, compared to the non-private  version, is image.png, assuming all the input data has bounded image.png norm. This is the first differentially private algorithm that achieves such a bound without the polynomial dependence on p under no additional assumptions on the design matrix. In addition, we show that this error bound is nearly optimal amongst all differentially private algorithms.

上一篇：Private Graphon Estimation for Sparse Graphs

下一篇：Learning to Linearize Under Uncertainty

用户评价
全部评价

热门资源

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...