{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005715518,0.0009087312,0.0009650196,0.0004877223,0.0003982837,0.0007575553,0.001240307,0.001248843,0.003976153],"category_scores_gemma":[0.001567097,0.0004091899,0.0008260963,0.0004536192,0.0008204737,0.0007625152,0.001464526,0.002013443,0.001563012],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005337519,"about_ca_system_score_gemma":0.000982153,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002277622,"about_ca_topic_score_gemma":0.003021176,"domain_scores_codex":[0.9997563,0.00007591597,0.00001064984,0.00002746832,0.0001141184,0.00001552581],"domain_scores_gemma":[0.9995477,0.0002063707,0.00002992543,0.00004547504,0.0001191637,0.00005139815],"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":[0.0002801785,0.000128746,0.0003683102,0.0004041668,0.0001316071,0.0001269354,0.0001540468,0.5144657,0.02392223,0.2119664,0.0146464,0.2334052],"study_design_scores_gemma":[0.00001024076,0.00002296533,0.00003182254,0.000007649501,0.000005313714,0.00001584967,0.000003031746,0.9853873,0.0009798311,0.01019714,0.003331132,0.000007784204],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002847069,0.000228039,0.9939265,0.0001006414,0.0001333841,0.00002486316,0.00004563616,0.0004395646,0.002254312],"genre_scores_gemma":[0.08964574,0.0004125039,0.8918499,0.0001825164,0.0001921227,0.0002368673,0.000193314,0.0008612986,0.01642582],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003976153,"threshold_uncertainty_score":0.01330161,"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."}}