{"id":"W4415482185","doi":"10.1109/tsp.2025.3624791","title":"Regularized Top-$ k $: A Bayesian Framework for Gradient Sparsification","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Signal Processing","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ericsson (Canada); University of Toronto","funders":"","keywords":"Scaling; Posterior probability; Convergence (economics); Rate of convergence; Bayesian probability; Prior probability; Generalization; Inverse; Inverse problem","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":[0.002337834,0.0009723133,0.001171586,0.000820027,0.0005935921,0.001433756,0.002384274,0.001423137,0.003701375],"category_scores_gemma":[0.008305702,0.0009655309,0.0009535658,0.0007059618,0.002013236,0.002447292,0.002127969,0.002745222,0.001587827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001076616,"about_ca_system_score_gemma":0.001625426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003428854,"about_ca_topic_score_gemma":0.004205418,"domain_scores_codex":[0.9990288,0.0003581137,0.00005774516,0.0001963752,0.0002788455,0.00008011864],"domain_scores_gemma":[0.9973001,0.001314062,0.0002657676,0.0005343375,0.0004591262,0.0001267043],"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":[0.0001983545,0.00005972398,0.0006931729,0.0001807691,0.00007823752,0.0001685583,0.0002067839,0.6049166,0.008967967,0.2211114,0.00382725,0.1595911],"study_design_scores_gemma":[0.00001129741,0.00001611501,0.00007269067,0.00001346283,0.000005470513,0.00003508651,0.000007062552,0.9641889,0.001762652,0.0323198,0.001554547,0.00001303046],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001257934,0.00003844496,0.9979772,0.00006238704,0.000008724701,0.0000166366,0.00002248664,0.0001369806,0.0004791477],"genre_scores_gemma":[0.09476154,0.0002209338,0.9005242,0.0001585747,0.00007153481,0.0001969534,0.0002683655,0.0003031308,0.003494749],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003701375,"threshold_uncertainty_score":0.01238239,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02870761014117459,"score_gpt":0.3225312797731015,"score_spread":0.2938236696319269,"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."}}