图 书 馆
通过稳定性论证选择差分私有特征，以及套索的鲁棒性Differentially Private Feature Selection via Stability Arguments, and the Robustness of the Lasso |
|
| 课程网址: | http://videolectures.net/colt2013_guha_thakurta_lasso/ |
| 主讲教师: | Abhradeep Guha Thakurta |
| 开课单位: | 微软公司 |
| 开课时间: | 2013-08-09 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | We design differentially private algorithms for statistical model selection. Given a data set and a large, discrete collection of “models”, each of which is a family of probability distributions, the goal is to determine the model that best “fits” the data. This is a basic problem in many areas of statistics and machine learning. We consider settings in which there is a well-defined answer, in the following sense: Suppose that there is a nonprivate model selection procedure f, which is the reference to which we compare our performance. Our differentially private algorithms output the correct value f(D) whenever f is stable on the input data set D. We work with two notions, perturbation stability and sub-sampling stability. We give two classes of results: generic ones, that apply to any function with discrete output set; and specific algorithms for the problem of sparse linear regression. The algorithms we describe are efficient and in some cases match the optimal non-private asymptotic sample complexity. Our algorithms for sparse linear regression require analyzing the stability properties of the popular LASSO estimator. We give sufficient conditions for the LASSO estimator to be robust to small changes in the data set, and show that these conditions hold with high probability under essentially the same stochastic assumptions that are used in the literature to analyze convergence of the LASSO. |
| 关 键 词: | 统计模型; 差异私有算法; 数据集; 离散模型集合; 概率分布; 渐进样本复杂度; 稀疏线性回归问题 |
| 课程来源: | 视频讲座网公开课 |
| 最后编审: | 2020-06-08：吴雨秋(课程编辑志愿者) |
| 阅读次数: | 80 |