{"id":"W2954099021","doi":"10.1016/j.neunet.2019.06.015","title":"Efficient inexact proximal gradient algorithms for structured sparsity-inducing norm","year":2019,"lang":"en","type":"article","venue":"Neural Networks","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"Priority Academic Program Development of Jiangsu Higher Education Institutions; Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Algorithm; Regularization (linguistics); Proximal Gradient Methods; Computer science; Operator (biology); Generalization; Norm (philosophy); Rate of convergence; Balanced flow; Convergence (economics); Mathematics; Mathematical optimization; Gradient descent; Key (lock); Artificial neural network; Artificial intelligence","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001956711,0.001482806,0.001515181,0.0008731023,0.0005644705,0.001423476,0.002162063,0.002135887,0.005513887],"category_scores_gemma":[0.009241063,0.0007801065,0.0007093556,0.001322406,0.00165279,0.002212728,0.003036078,0.004147342,0.001995251],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000948614,"about_ca_system_score_gemma":0.002204129,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002918464,"about_ca_topic_score_gemma":0.00509576,"domain_scores_codex":[0.9988683,0.0004062857,0.00005206774,0.0001357646,0.0004683626,0.00006930593],"domain_scores_gemma":[0.9972402,0.001692503,0.0001500632,0.0002815984,0.0004921919,0.0001434583],"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":[0.0003141867,0.000221423,0.0003765424,0.0004352622,0.00007995201,0.0001399859,0.0002169169,0.4851616,0.007194092,0.1749627,0.01426425,0.316633],"study_design_scores_gemma":[0.00001459297,0.00002917576,0.00003984239,0.00001427254,0.000004483906,0.00003520823,0.00001490586,0.9720713,0.001059227,0.02521698,0.001492217,0.000007697518],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001201326,0.00009864445,0.9977367,0.00008942117,0.0000328221,0.00002295304,0.00002584137,0.0001425161,0.0006498107],"genre_scores_gemma":[0.07419688,0.0003976019,0.9193594,0.0001414982,0.0001278493,0.0002235822,0.000277498,0.000270074,0.005005604],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005513887,"threshold_uncertainty_score":0.01844573,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01475702973620678,"score_gpt":0.2234007007286691,"score_spread":0.2086436709924623,"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."}}