{"id":"W4321636690","doi":"10.1109/sc41404.2022.00052","title":"HyLo: A Hybrid Low-Rank Natural Gradient Descent Method","year":2022,"lang":"en","type":"article","venue":"","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Kronecker delta; Scalability; Gradient descent; Computer science; Quadratic growth; Computation; Factorization; Algorithm; Stochastic gradient descent; Matrix decomposition; Residual neural network; Rank (graph theory); Artificial neural network; 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":[],"consensus_categories":[],"category_scores_codex":[0.0001010079,0.0001179657,0.0001240513,0.00007632409,0.0001012902,0.00002091548,0.0001623583,0.00001147495,0.0002348919],"category_scores_gemma":[0.000005375192,0.0001140097,0.00007371343,0.0001132759,0.000009323052,0.00003627656,0.0001132819,0.0002384505,0.00001193175],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001021243,"about_ca_system_score_gemma":0.000006436218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003721016,"about_ca_topic_score_gemma":0.000003527679,"domain_scores_codex":[0.9993017,0.0000425329,0.0001234801,0.0001481244,0.0001665959,0.0002175865],"domain_scores_gemma":[0.99967,0.00002900382,0.0000134663,0.0002268434,0.00001703521,0.00004363948],"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":[0.00008558732,0.0002882837,0.0001968975,0.00007551222,0.0003725465,0.0006630002,0.0008732895,0.1424371,0.2507071,0.01888554,0.4210437,0.1643714],"study_design_scores_gemma":[0.0002968211,0.00006721839,0.0002714408,0.00001910546,0.00002312211,0.0002108887,0.0001053088,0.5008291,0.4201522,0.002976718,0.07460895,0.0004391569],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5255532,0.002237958,0.434192,0.0003522987,0.002936037,0.0006126324,0.00001984554,0.006567295,0.0275287],"genre_scores_gemma":[0.9759173,0.00001572791,0.02342259,0.0002563109,0.00004469029,0.00002896654,0.000007762376,0.00002745417,0.000279183],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4503641,"threshold_uncertainty_score":0.464918,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009293411424507457,"score_gpt":0.2278365780491658,"score_spread":0.2185431666246584,"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."}}