{"id":"W2963248893","doi":"10.1007/978-3-319-46128-1_50","title":"Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Łojasiewicz Condition","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":832,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Convexity; Rate of convergence; Applied mathematics; Mathematics; Stochastic gradient descent; Convergence (economics); Gradient descent; Mathematical proof; Generalization; Simple (philosophy); Convex function; Regular polygon; Mathematical optimization; Computer science; Mathematical analysis; Artificial neural network; Artificial intelligence; Geometry","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":[0.004151328,0.002422076,0.002131816,0.001761552,0.0009485255,0.0024209,0.002601948,0.003166152,0.00664907],"category_scores_gemma":[0.02026464,0.0012,0.001658539,0.002122345,0.004622892,0.004621867,0.005113363,0.00649016,0.002435806],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00210358,"about_ca_system_score_gemma":0.002675335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004509287,"about_ca_topic_score_gemma":0.002702877,"domain_scores_codex":[0.9980732,0.0009052703,0.00007612834,0.000264585,0.0005246105,0.0001562319],"domain_scores_gemma":[0.9937031,0.004480813,0.0002914511,0.000333815,0.0008952499,0.0002956958],"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":[0.0002636377,0.00009401357,0.0002826552,0.0005630734,0.00008455467,0.0000903968,0.0002683846,0.1353237,0.002085882,0.794345,0.01052876,0.05606997],"study_design_scores_gemma":[0.00003849199,0.00005553477,0.0001609013,0.00007322799,0.00002096415,0.00007348761,0.00003472249,0.6326576,0.0008239567,0.3615146,0.004509497,0.00003706985],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005550675,0.002804835,0.9717295,0.0009241711,0.0003935179,0.0000508765,0.00008592614,0.000214555,0.01824589],"genre_scores_gemma":[0.3076894,0.008777295,0.5827145,0.0009052804,0.001515148,0.0008417721,0.0006721281,0.001597445,0.09528704],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00664907,"threshold_uncertainty_score":0.02224338,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0238326173554937,"score_gpt":0.2977316453413589,"score_spread":0.2738990279858652,"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."}}