Table 2 The various parameter values that comprised experimental setup tested on synthetic datasets
From: Sarve: synthetic data and local differential privacy for private frequency estimation
Experimental setup identifier | Values of ε | Dataset name | Number of observations = N | Number of categorical attributes = D | Number of allowed values for each attribute = A |
|---|---|---|---|---|---|
ES_Syn_1 | [ln(2), ln(3), ln(4), ln(5), ln(6), ln(7)] | 50K_5D | 50,000 | 5 | [10, 10, 10, 10, 10] |
ES_Syn_2 | [ln(2), ln(3), ln(4), ln(5), ln(6), ln(7)] | 50K_10D | 50,000 | 10 | [10, 10, 10, 10, 10, 10, 10, 10, 10, 10] |
ES_Syn_3 | [ln(2), ln(3), ln(4), ln(5), ln(6), ln(7)] | 500K_5D | 500,000 | 5 | [10, 10, 10, 10, 10] |
ES_Syn_4 | [ln(2), ln(3), ln(4), ln(5), ln(6), ln(7)] | 500K_10D | 500,000 | 10 | [10, 10, 10, 10, 10, 10, 10, 10, 10, 10] |
ES_Syn_5 | [ln(2), ln(3), ln(4), ln(5), ln(6), ln(7)] | 500K_10D_NU | 500,000 | 10 | [10, 20, 30, 40, 50, 60, 70, 80, 90, 100] |
ES_Syn_6 | [ln(2), ln(3), ln(4), ln(5), ln(6), ln(7)] | 500K_20D_NU | 500,000 | 20 | [10, 10, 20, 20, 30, 30, 40, 40, 50, 50, 60, 60, 70, 70, 80, 80, 90, 90, 100, 100] |
ES_Syn_7 | [2, 3, 4, 5, 6, 7] | 50K_5 D | 50,000 | 5 | [10, 10, 10, 10, 10] |
ES_Syn_8 ara> | [2, 3, 4, 5, 6, 7] | 50K_10 D | 50,000 | 10 | [10, 10, 10, 10, 10, 10, 10, 10, 10, 10] |
ES_Syn_9 | [2, 3, 4, 5, 6, 7] | 500K_5D | 500,000 | 5 | [10, 10, 10, 10, 10] |
ES_Syn_10 | [2, 3, 4, 5, 6, 7] | 500K_10D | 500,000 | 10 | [10, 10, 10, 10, 10, 10, 10, 10, 10, 10] |
ES_Syn_11 | [2, 3, 4, 5, 6, 7] | 500K_10D_NU | 500,000 | 10 | [10, 20, 30, 40, 50, 60, 70, 80, 90, 100] |
ES_Syn_12 | [2, 3, 4, 5, 6, 7] | 500K_20D_NU | 500,000 | 20 | [10, 10, 20, 20, 30, 30, 40, 40, 50, 50, 60, 60, 70, 70, 80, 80, 90, 90, 100, 100] |