{"id":"W2768739050","doi":"10.1093/imaiai/iay019","title":"Near-optimal sample complexity for convex tensor completion","year":2018,"lang":"en","type":"preprint","venue":"Information and Inference A Journal of the IMA","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia Hospital","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Tensor (intrinsic definition); Minimax; Combinatorics; Matrix norm; Rank (graph theory); Norm (philosophy); Matrix completion; Regular polygon; Low-rank approximation; Mathematical optimization; Pure mathematics; Physics; Geometry","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0002182045,0.0001439583,0.0002617369,0.00007658268,0.000119636,0.0002468961,0.0002690268,0.0001162421,0.0000264665],"category_scores_gemma":[0.0002015208,0.0001028821,0.0001154687,0.0000413273,0.0001573356,0.0003997298,0.0001495115,0.0003365971,0.000003670298],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004452533,"about_ca_system_score_gemma":0.00006904457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002347086,"about_ca_topic_score_gemma":0.000002624318,"domain_scores_codex":[0.9991376,0.00002153915,0.0005085677,0.0000438708,0.0001681248,0.0001203418],"domain_scores_gemma":[0.9986992,0.00009817389,0.0004198252,0.0001829612,0.0005539255,0.00004585948],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001315896,0.000209861,0.01391105,0.003106663,0.001863777,0.000004550117,0.02054386,0.3490543,0.003319584,0.02097411,0.3852769,0.2004195],"study_design_scores_gemma":[0.0006607886,0.0001855049,0.01303209,0.0007803503,0.00008142855,0.0000818616,0.0001312095,0.8716843,0.004242289,0.02472501,0.08404806,0.0003471611],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4348145,0.0001177394,0.5623331,0.0004599997,0.001064772,0.0003877671,0.0001460777,0.0001086649,0.0005673693],"genre_scores_gemma":[0.9640673,0.0001145703,0.03535419,0.000285293,0.0001406465,0.000005273741,0.00002169908,0.000008448506,0.000002586812],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5292528,"threshold_uncertainty_score":0.4195411,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04930836521229182,"score_gpt":0.2818386328107859,"score_spread":0.232530267598494,"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."}}