{"id":"W4406448033","doi":"10.48550/arxiv.2501.07433","title":"Equivalence between exponential concentration in quantum machine learning kernels and barren plateaus in variational algorithms","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Stewart Blusson Quantum Matter Institute, University of British Columbia; Natural Sciences and Engineering Research Council of Canada","keywords":"Equivalence (formal languages); Exponential function; Algorithm; Quantum; Computer science; Mathematics; Artificial intelligence; Discrete mathematics; Applied mathematics; Theoretical computer science; Pure mathematics; Physics; Quantum mechanics; Mathematical analysis","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000365847,0.0002159324,0.0002902955,0.0001189612,0.0001039668,0.0001292941,0.0006052424,0.0001880156,0.00001157622],"category_scores_gemma":[0.00003935821,0.0002318303,0.00004366974,0.0003361114,0.0000434028,0.0002488164,0.0009602978,0.0008489899,0.000008695123],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000764439,"about_ca_system_score_gemma":0.0001284266,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005427187,"about_ca_topic_score_gemma":0.000054226,"domain_scores_codex":[0.9981493,0.0001486506,0.0004692533,0.0007245339,0.0002143634,0.0002939223],"domain_scores_gemma":[0.9991327,0.0002347471,0.0001904225,0.0003277762,0.00004294574,0.00007140004],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000005179017,0.00004390478,0.9620569,0.00004001195,0.00001644648,0.00001126934,0.0004256691,0.02236155,0.0002007468,0.005868152,0.00002269252,0.008947503],"study_design_scores_gemma":[0.000281831,0.0000132696,0.5196954,0.0001287661,0.000006325008,0.000001113822,0.00000437792,0.476538,0.0001173325,0.002892592,0.0001469837,0.000173963],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8189216,0.0003862906,0.1787227,0.001022925,0.0003501654,0.0003893269,0.00002875799,0.00007478302,0.0001034605],"genre_scores_gemma":[0.9966258,0.0002571776,0.002514565,0.00006833047,0.0001970454,0.00008260228,0.0001335971,0.000007309328,0.0001135262],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4541765,"threshold_uncertainty_score":0.9453766,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04978411328209734,"score_gpt":0.2949332914206484,"score_spread":0.2451491781385511,"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."}}