{"id":"W2912255742","doi":"10.1007/978-3-030-10928-8_21","title":"MASAGA: A Linearly-Convergent Stochastic First-Order Method for Optimization on Manifolds","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Rate of convergence; Stochastic gradient descent; Variance reduction; Riemannian manifold; Convergence (economics); Manifold (fluid mechanics); Applied mathematics; Eigenvalues and eigenvectors; Computer science; Mathematical optimization; Stochastic optimization; Mathematics; Variance (accounting); Gradient descent; Convex function; Regular polygon; Mathematical analysis; Key (lock); Artificial intelligence; Statistics; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009915797,0.0007395722,0.0006965635,0.001330827,0.000295652,0.0005103282,0.002971326,0.000481912,0.00005463355],"category_scores_gemma":[0.0003559296,0.0007060221,0.0002054163,0.0008430041,0.0002287601,0.0004812389,0.0008682749,0.0005643563,0.00004474459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005010555,"about_ca_system_score_gemma":0.000617011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001133438,"about_ca_topic_score_gemma":0.00001672608,"domain_scores_codex":[0.9952486,0.00003644522,0.0007217142,0.002128251,0.001093276,0.0007716742],"domain_scores_gemma":[0.9955671,0.001316337,0.0004884938,0.001723849,0.0007072856,0.0001969211],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000142766,0.00003570937,0.000001935351,0.00004621458,0.00001478959,0.000005561767,0.0002019981,0.9023377,0.000003891318,0.06154899,0.00007037184,0.03571861],"study_design_scores_gemma":[0.0004653358,0.0005859187,0.000005207397,0.0003998291,0.00001857439,0.00002512369,9.869314e-8,0.9584059,0.0001810344,0.03876877,0.0004271201,0.0007170452],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[5.054117e-7,0.00009459993,0.9925048,0.00131927,0.002830312,0.002008594,0.00001727832,0.0004193365,0.0008052544],"genre_scores_gemma":[0.001361131,0.00001440401,0.9952123,0.00212253,0.0003063836,0.00008421818,0.00002387591,0.00007908976,0.0007961358],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.05606829,"threshold_uncertainty_score":0.9995391,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01913421443365014,"score_gpt":0.2667438314597867,"score_spread":0.2476096170261365,"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."}}