{"id":"W3112516868","doi":"10.48550/arxiv.2012.05782","title":"A Study of Condition Numbers for First-Order Optimization","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Convexity; Smoothness; Mathematical optimization; Norm (philosophy); Perturbation (astronomy); Gradient descent; Hyperparameter; Mathematics; Convergence (economics); Computer science; Applied mathematics; Optimization problem; Uniform norm; Algorithm; Artificial intelligence; Discrete mathematics; Mathematical analysis; Artificial neural network","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008348374,0.00188652,0.001238301,0.001889302,0.001224608,0.00361975,0.001622975,0.002610946,0.007720557],"category_scores_gemma":[0.05602307,0.000570945,0.001163096,0.001444901,0.00592945,0.006147751,0.002264114,0.006540303,0.001208591],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002801524,"about_ca_system_score_gemma":0.002289891,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001806769,"about_ca_topic_score_gemma":0.0009246044,"domain_scores_codex":[0.9965184,0.001384023,0.0001566942,0.0005253581,0.001145399,0.0002700947],"domain_scores_gemma":[0.961371,0.03171822,0.001879766,0.001623867,0.002516744,0.0008904256],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000389672,0.00002395424,0.0002737503,0.0001725909,0.00001611383,0.00004924925,0.00009236093,0.04893191,0.001595107,0.9381623,0.002072731,0.008571118],"study_design_scores_gemma":[0.0000126998,0.00007619811,0.0002345094,0.0001091739,0.00001035518,0.00006470483,0.0000359439,0.4923705,0.001449953,0.5011637,0.004441882,0.00003035524],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01791677,0.00310652,0.9362804,0.003349198,0.0004049526,0.0000834291,0.0001834057,0.000267378,0.03840802],"genre_scores_gemma":[0.6634173,0.006296917,0.306719,0.001579619,0.001135459,0.0007191514,0.0004597809,0.0008781606,0.01879464],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008348374,"threshold_uncertainty_score":0.04415095,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08323042211128721,"score_gpt":0.2011218476139263,"score_spread":0.117891425502639,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}