{ "bench_version": 1, "track": "tabular", "model": "mlp_tiny", "metric_direction": "lower is better", "n_seeds": 8, "baseline": { "best_cfg": { "lr": 0.006, "epsilon": 0.03 }, "sweep": [ { "cfg": { "lr": 0.0015, "epsilon": 0.03 }, "mean": 16.612406492233276 }, { "cfg": { "lr": 0.0015, "epsilon": 0.06 }, "mean": 16.47487497329712 }, { "cfg": { "lr": 0.0015, "epsilon": 0.12 }, "mean": 16.447417736053467 }, { "cfg": { "lr": 0.003, "epsilon": 0.03 }, "mean": 12.79465126991272 }, { "cfg": { "lr": 0.003, "epsilon": 0.06 }, "mean": 12.77505874633789 }, { "cfg": { "lr": 0.003, "epsilon": 0.12 }, "mean": 12.748817920684814 }, { "cfg": { "lr": 0.006, "epsilon": 0.03 }, "mean": 9.08214282989502 }, { "cfg": { "lr": 0.006, "epsilon": 0.06 }, "mean": 9.164641618728638 }, { "cfg": { "lr": 0.006, "epsilon": 0.12 }, "mean": 9.159956216812134 } ], "full": { "mean": 9.39148885011673, "std": 1.1083451358712588, "per_seed": [ 8.348429679870605, 10.594329833984375, 8.394119262695312, 8.991692543029785, 7.703206539154053, 9.93536376953125, 10.861209869384766, 10.303559303283691 ], "n": 8 } }, "idea": { "mean": 9.156296849250793, "std": 1.1388098507230549, "per_seed": [ 7.9084343910217285, 10.600011825561523, 8.813246726989746, 8.956066131591797, 7.3792853355407715, 8.759374618530273, 10.619342803955078, 10.21461296081543 ], "n": 8 }, "comparison": { "delta_mean": -0.23519200086593628, "idea_wins": 6, "n_pairs": 8, "per_seed_diffs": [ -0.43999528884887695, 0.0056819915771484375, 0.4191274642944336, -0.03562641143798828, -0.32392120361328125, -1.1759891510009766, -0.2418670654296875, -0.08894634246826172 ], "p_value": 0.18585, "mde": 0.38477736395591483, "mde_rel_pct": 4.097085883790751, "verdict": "no significant win", "system_worked": false }, "mechanism_signature": { "track_match": "optimizer noise -> tabular Friedman#1", "mechanism": { "prediction": "compensated small-jump update variance equals scale^2*c*epsilon^(2-alpha)/(2-alpha)", "predicted_update_variance": 4.898979485566358e-08, "observed_update_variance": 4.051713719621018e-08, "relative_error": 0.17294740025787028, "confirmed": false, "trained_model_runs": 8, "selected_cfg": { "lr": 0.006, "epsilon": 0.06 }, "idea_settings_evaluated": [ { "cfg": { "lr": 0.006, "epsilon": 0.06 }, "result": { "mean": 9.156296849250793, "std": 1.1388098507230549, "per_seed": [ 7.9084343910217285, 10.600011825561523, 8.813246726989746, 8.956066131591797, 7.3792853355407715, 8.759374618530273, 10.619342803955078, 10.21461296081543 ], "n": 8 } }, { "cfg": { "lr": 0.006, "epsilon": 0.03 }, "result": { "mean": 9.438631236553192, "std": 1.0926888335764746, "per_seed": [ 8.160052299499512, 10.666433334350586, 8.840189933776855, 8.998281478881836, 7.716319561004639, 10.017929077148438, 10.732819557189941, 10.37702465057373 ], "n": 8 } }, { "cfg": { "lr": 0.006, "epsilon": 0.12 }, "result": { "mean": 9.451428532600403, "std": 1.0498153270226125, "per_seed": [ 8.208366394042969, 10.474081039428711, 8.878252983093262, 9.130773544311523, 7.725558280944824, 10.141274452209473, 10.64528751373291, 10.40783405303955 ], "n": 8 } } ] } }, "idea_sweep": [ { "cfg": { "lr": 0.006, "epsilon": 0.06 }, "result": { "mean": 9.156296849250793, "std": 1.1388098507230549, "per_seed": [ 7.9084343910217285, 10.600011825561523, 8.813246726989746, 8.956066131591797, 7.3792853355407715, 8.759374618530273, 10.619342803955078, 10.21461296081543 ], "n": 8 } }, { "cfg": { "lr": 0.006, "epsilon": 0.03 }, "result": { "mean": 9.438631236553192, "std": 1.0926888335764746, "per_seed": [ 8.160052299499512, 10.666433334350586, 8.840189933776855, 8.998281478881836, 7.716319561004639, 10.017929077148438, 10.732819557189941, 10.37702465057373 ], "n": 8 } }, { "cfg": { "lr": 0.006, "epsilon": 0.12 }, "result": { "mean": 9.451428532600403, "std": 1.0498153270226125, "per_seed": [ 8.208366394042969, 10.474081039428711, 8.878252983093262, 9.130773544311523, 7.725558280944824, 10.141274452209473, 10.64528751373291, 10.40783405303955 ], "n": 8 } } ], "custom_track": null }