Complete result settings for Ad dataset (table columns are sortable)
The experiments are described in Rooshenas and Lowd, Discriminative Structure Learning of Arithmetic Circuits, AIStats 16
Standard Deviation | L1 Penalty | Train CLL | Validation CLL | Test CLL | Node# | Edge# | Feature# | Learning Time |
0.1 | 2 | -2.050823 | -2.464985 | -2.250721 | 253628 | 565827 | 9740 | 26083.187752 |
0.1 | 10 | -5.371246 | -6.338194 | -5.598875 | 253628 | 565827 | 9740 | 26455.089214 |
0.1 | 5 | -4.786776 | -5.441229 | -4.918045 | 253628 | 565827 | 9740 | 27339.039833 |
0.1 | 1 | -1.416551 | -1.790333 | -1.627554 | 253628 | 565827 | 9740 | 26657.127500 |
0.1 | 0.5 | -1.246144 | -1.607855 | -1.505323 | 253628 | 565827 | 9740 | 34530.079629 |
0.1 | 0.1 | -1.440522 | -1.747159 | -1.658494 | 253628 | 565827 | 9740 | 54155.037182 |