{"id":"W2963201904","doi":"","title":"Dimensionality Reduction has Quantifiable Imperfections: Two Geometric Bounds","year":2018,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Topological and Geometric Data Analysis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University of Alberta","funders":"","keywords":"Measure (data warehouse); Dimensionality reduction; Mathematical proof; Computer science; Reduction (mathematics); Lipschitz continuity; Key (lock); Curse of dimensionality; Algorithm; Mathematics; Mathematical optimization; Point (geometry); Set (abstract data type); Topology (electrical circuits); Data mining; 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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007678242,0.0001555138,0.0002175044,0.0008937427,0.001144802,0.00213333,0.0005062175,0.00007855865,0.00003127165],"category_scores_gemma":[0.0002436179,0.0001193437,0.00006978802,0.005587026,0.0001585329,0.007281304,0.0001556167,0.0001447161,0.0003963346],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008858754,"about_ca_system_score_gemma":0.00008631773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006526585,"about_ca_topic_score_gemma":0.000003221934,"domain_scores_codex":[0.9981619,0.0000833963,0.0006380479,0.0002746195,0.0005331672,0.0003088984],"domain_scores_gemma":[0.9983407,0.00005046876,0.0004046921,0.0004304287,0.0006647225,0.000108942],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000764653,0.0004309486,0.002873903,0.0006770668,0.0001721866,0.000006024821,0.002694891,0.0150055,0.001915322,0.09530631,0.07187714,0.8089643],"study_design_scores_gemma":[0.0005872758,0.0003010697,0.002413888,0.00006288942,0.00003466091,0.0003318167,0.0004123943,0.8561615,0.001343454,0.001208795,0.1366591,0.000483232],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1365322,0.0008194171,0.8505571,0.001538314,0.003502234,0.0003968884,0.0000158614,0.0009693666,0.005668554],"genre_scores_gemma":[0.9975932,0.000005996478,0.001433461,0.0001587624,0.0002709999,0.00002729946,0.00004620893,0.000003448206,0.0004606288],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.861061,"threshold_uncertainty_score":0.9989026,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04108341971202272,"score_gpt":0.2859869168908117,"score_spread":0.244903497178789,"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."}}