Separable Ky-Fan spectral regularization / results.json

Mechanism confirmed, baseline not beaten

Raw ⬇ ZIP
 1{
 2  "seed": 1729,
 3  "verification": {
 4    "trials": 100,
 5    "failures": 0,
 6    "worst_cumulative_gap": 3.183231456205249e-12,
 7    "max_gap_by_k": [
 8      0.0,
 9      0.0,
10      0.0,
11      0.0,
12      0.0,
13      0.0,
14      0.0,
15      0.0,
16      0.0,
17      0.0,
18      0.0,
19      0.0,
20      0.0,
21      0.0,
22      0.0,
23      0.0,
24      0.0,
25      0.0,
26      0.0,
27      0.0,
28      0.0,
29      0.0,
30      0.0,
31      0.0,
32      0.0,
33      0.0,
34      3.183231456205249e-12
35    ],
36    "max_eigenvalue_ratio_mean": 0.7369189783558373,
37    "max_eigenvalue_ratio_min": 0.5273421323723241,
38    "max_eigenvalue_ratio_max": 0.9760578231973766
39  },
40  "training": [
41    {
42      "mode": "baseline",
43      "device": "cuda",
44      "final_loss": 0.06210070103406906,
45      "best_loss": 0.055831555277109146,
46      "steps_completed": 250,
47      "nonfinite_steps": 0,
48      "max_exact_norm": 2.679940700531006,
49      "final_exact_norm": 0.7381001114845276,
50      "final_R1": 1.111295461654663,
51      "norm_over_R1": 0.6641799026026198,
52      "seconds": 10.995668057999865
53    },
54    {
55      "mode": "penalty",
56      "device": "cuda",
57      "final_loss": 0.07478956878185272,
58      "best_loss": 0.06771540641784668,
59      "steps_completed": 250,
60      "nonfinite_steps": 0,
61      "max_exact_norm": 2.1669960021972656,
62      "final_exact_norm": 0.7399500608444214,
63      "final_R1": 0.8184396624565125,
64      "norm_over_R1": 0.9040984873869531,
65      "seconds": 14.601756300999114
66    },
67    {
68      "mode": "controller",
69      "device": "cuda",
70      "final_loss": 0.07558591663837433,
71      "best_loss": 0.06306523829698563,
72      "steps_completed": 250,
73      "nonfinite_steps": 0,
74      "max_exact_norm": 373.8607177734375,
75      "final_exact_norm": 339.4143371582031,
76      "final_R1": 625.4991455078125,
77      "norm_over_R1": 0.5426295776673669,
78      "seconds": 14.152621004999673
79    }
80  ]
81}