{"id":"W7117471539","doi":"10.1109/ton.2025.3649391","title":"Nested Quasi-Newton Optimization for Federated Learning Under Periodic Deterministic Communication Constraints","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Networking","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Leverage (statistics); Robustness (evolution); Federated learning; Convergence (economics); Benchmark (surveying); Global optimization; Optimization problem; Premature convergence","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.001019027,0.0005938482,0.0005948617,0.0006504526,0.00363374,0.001489032,0.009277064,0.0006641508,0.0000760625],"category_scores_gemma":[0.0009922803,0.0007333131,0.0002413534,0.002138754,0.000752144,0.0007642081,0.0006763401,0.001473204,0.00001487248],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005813031,"about_ca_system_score_gemma":0.0005384995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004193935,"about_ca_topic_score_gemma":0.00008884207,"domain_scores_codex":[0.9957119,0.0006844777,0.001076016,0.001214716,0.0003832325,0.0009296906],"domain_scores_gemma":[0.9920384,0.00196328,0.0005199122,0.004994022,0.0003651702,0.0001192706],"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":[0.0000961609,0.0002528661,0.0000186586,0.0000998205,0.0001624192,0.000003594683,0.0001534632,0.6129727,0.00007804551,0.0002935654,0.001441547,0.3844272],"study_design_scores_gemma":[0.001352787,0.0003164107,0.00001730508,0.001737804,0.0001997551,0.00001954756,0.0002847838,0.9888748,0.0008275382,0.00461751,0.001175455,0.0005762978],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007525617,0.0006434435,0.9819108,0.01003136,0.003686797,0.001324831,0.00003053075,0.001226196,0.0003934904],"genre_scores_gemma":[0.8721425,0.001192444,0.1254985,0.000418734,0.00006769454,0.0002442918,0.00005435781,0.00005602172,0.0003254538],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8713899,"threshold_uncertainty_score":0.9995475,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04050586423524514,"score_gpt":0.2979850448790511,"score_spread":0.257479180643806,"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."}}