Some content of this application is unavailable at the moment.
1. (WO2019007417) TRAINING SAMPLE GENERATION METHOD AND DEVICE BASED ON PRIVACY PROTECTION
Document

## 发明名称 : 基于隐私保护的训练样本生成方法和装置

[0001]

[0002]

[0003]

[0004]

[0005]

[0006]

[0007]

[0008]

[0009]

[0010]

[0011]

[0012]

[0013]

[0014]

[0015]

[0016]

[0017]

[0018]

[0019]

[0020]

[0021]

[0022]

[0023]

[0024]

[0025]

[0026]

[0027]

### 具体实施方式

[0028]

[0029]

[0030]

[0031]

[0032]

[0033]

[0034]

[0035]

[0036]

[0037]

[0038]

[0039]

[0040]

[0041]
Y(x)＝θ Tx 式1
[0042]

[0043]
[0044]

[0045]

[0046]
Y(π)＝θ Tπ 式3
[0047]

[0048]
[0049]

[0050]

[0051]

[0052]
[0053]
[0054]

[0055]
[0056]

[0057]

[0058]

[0059]

[0060]

[0061]

[0062]

[0063]

[0064]

[0065]

[0066]

[0067]
Boosting算法的初始化：设n个转换向量π构成的样本空间为：δ r＝{π 12,…,π n}；预设Boosting算法的迭代次数T(T为自然数)；将线性模型θ的初始值θ 0置为d维的0向量；将n维中间变量ω的初始值ω 1置为每个维度均等于1/n；预先计算π *k，k为从1到d的每个自然数，π *k为n个转换向量π在第k个维度的最大值。
[0068]
Boosting算法的从第1轮到第T轮的迭代过程：
[0069]

[0070]
[0071]
[0072]

[0073]
[0074]

[0075]

[0076]
[0077]

[0078]

[0079]

[0080]

[0081]

[0082]

[0083]

[0084]

[0085]
[0086]

[0087]
[0088]

[0089]

[0090]

[0091]

[0092]

[0093]

[0094]

[0095]

[0096]

[0097]

[0098]

[0099]

[0100]

[0101]

[0102]

[0103]

[0104]

[0105]

[0106]

[0107]

[0108]

[0109]

[0110]

[0111]

[0112]

[0113]

[0114]

[权利要求 1]

[权利要求 2]

[权利要求 3]

[权利要求 4]

[权利要求 5]

[权利要求 6]

[权利要求 7]

[权利要求 8]

[权利要求 9]

[权利要求 10]

[权利要求 11]

[权利要求 12]

[权利要求 13]

[权利要求 14]

[ 图 1]
[ 图 2]
[ 图 3]
[ 图 4]
[ 图 5]
[ 图 6]