{"id":"W1522301498","doi":"10.48550/arxiv.1412.6980","title":"Adam: A Method for Stochastic Optimization","year":2014,"lang":"en","type":"preprint","venue":"UvA-DARE (University of Amsterdam)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":84783,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Regret; Mathematical optimization; Computer science; Diagonal; Convergence (economics); Stochastic optimization; Rate of convergence; Optimization problem; Mathematics; Key (lock); Machine learning","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":[0.002091597,0.002131533,0.001959663,0.0008078784,0.0006086195,0.002179903,0.002379986,0.002511458,0.005956917],"category_scores_gemma":[0.006962539,0.001046243,0.00119912,0.0009757245,0.001689104,0.001983238,0.002792973,0.004100027,0.003399273],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008394011,"about_ca_system_score_gemma":0.001830585,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001740989,"about_ca_topic_score_gemma":0.002154346,"domain_scores_codex":[0.9984296,0.0006831514,0.0001133769,0.0002386052,0.0004497024,0.00008548558],"domain_scores_gemma":[0.9979012,0.001287078,0.0002068297,0.0001969585,0.0002874477,0.0001204911],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000986482,0.00004229782,0.0005480289,0.0004442873,0.0001843592,0.0002467397,0.0001211376,0.6600494,0.002924374,0.1992064,0.02881358,0.1073207],"study_design_scores_gemma":[0.0000155567,0.00001836192,0.00004666455,0.00002878577,0.000009614378,0.00007413543,0.000005966088,0.925297,0.0006983391,0.06148333,0.01230713,0.00001526535],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004418518,0.0003868858,0.9968882,0.0003422448,0.00009725681,0.00002314736,0.00007227437,0.0004635255,0.001284627],"genre_scores_gemma":[0.06240457,0.001785464,0.9222605,0.000549945,0.0004845559,0.0004774033,0.0006331974,0.00120291,0.01020139],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005956917,"threshold_uncertainty_score":0.01992786,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01871386613063046,"score_gpt":0.2485319222798558,"score_spread":0.2298180561492253,"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."}}