{"id":"W3023705181","doi":"10.36227/techrxiv.12199026.v1","title":"A non-convex optimization framework for large-scale low-rank matrix factorization","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Non-negative matrix factorization; Dimensionality reduction; Hessian matrix; Matrix decomposition; Rank (graph theory); Matrix (chemical analysis); Mathematics; Factorization; Conjugate gradient method; Low-rank approximation; Algorithm; Mathematical optimization; Convergence (economics); Computer science; Reduction (mathematics); Applied mathematics; Artificial intelligence; Combinatorics","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":[0.00005458982,0.0003261112,0.0003949287,0.0001026975,0.0000554816,0.0001273625,0.0002475542,0.0006314608,0.0001139939],"category_scores_gemma":[0.00004040658,0.0003493011,0.0001677791,0.0001308603,0.000009056232,0.00007210726,0.0001768421,0.0004611667,0.00001594295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006773997,"about_ca_system_score_gemma":0.00002943761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007779654,"about_ca_topic_score_gemma":0.000002211026,"domain_scores_codex":[0.9988699,0.0000111255,0.0003159393,0.0003852579,0.0001542598,0.000263543],"domain_scores_gemma":[0.9992246,0.00005654101,0.00008356301,0.0004265321,0.0001268651,0.00008188887],"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":[0.0000179946,0.00002560955,0.00005734109,0.0004016279,0.00009640777,0.000002227393,0.0004308594,0.986429,0.0009985948,0.002241991,0.008992004,0.0003062955],"study_design_scores_gemma":[0.0001482192,0.00001966202,0.00002841303,0.0003103587,0.0000505545,5.592085e-7,0.00003157925,0.9620951,0.0215662,0.01409906,0.001260684,0.0003895602],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006883168,0.0001115409,0.9932838,0.0001612057,0.001117321,0.0009228251,0.00007898024,0.00242632,0.001209687],"genre_scores_gemma":[0.4710626,0.0001723408,0.5273334,0.0001253653,0.0005112731,0.0001214139,0.0004841446,0.0001198442,0.00006962825],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4703743,"threshold_uncertainty_score":0.9998959,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01700254015231117,"score_gpt":0.2685198352883177,"score_spread":0.2515172951360066,"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."}}