{"id":"W4417298805","doi":"10.48550/arxiv.2505.14371","title":"Layer-wise Quantization for Quantized Optimistic Dual Averaging","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Army Research Office; Centers for Disease Control and Prevention; National Supercomputing Centre Singapore; Norges Forskningsråd; Institute for Catastrophic Loss Reduction; Hasler Stiftung; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Centro Svizzero di Calcolo Scientifico; National Science Foundation","keywords":"Quantization (signal processing); Speedup; Monotone polygon; Convergence (economics); Representation (politics); Artificial neural network; Dual (grammatical number)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00136621,0.0007094537,0.000740022,0.0003470003,0.000426929,0.0009867704,0.001666187,0.00070064,0.003395213],"category_scores_gemma":[0.005169339,0.0003696855,0.0004519515,0.0004555746,0.0008912414,0.001617662,0.002105504,0.002156209,0.0005533216],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009813785,"about_ca_system_score_gemma":0.001142823,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002241416,"about_ca_topic_score_gemma":0.003572789,"domain_scores_codex":[0.999177,0.0002620992,0.00005506424,0.000153231,0.0002665064,0.00008617058],"domain_scores_gemma":[0.9990363,0.0003923231,0.0000788265,0.0002178644,0.0002083245,0.00006641434],"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":[0.0002718662,0.00008568146,0.001177298,0.0001152908,0.00005770359,0.00009281452,0.0001584806,0.6614628,0.01279928,0.1477264,0.005667046,0.1703854],"study_design_scores_gemma":[0.000007294997,0.0000197517,0.00004277628,0.000004461121,0.000003023333,0.00001398233,0.00000621774,0.9771852,0.001557578,0.02053705,0.0006179003,0.000004909662],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0111468,0.0001957133,0.9859769,0.00021551,0.00005426936,0.00003265826,0.00007352026,0.0005705716,0.00173391],"genre_scores_gemma":[0.6337983,0.0002268371,0.3612272,0.0003337328,0.0001007825,0.0001621185,0.0003176115,0.0003216293,0.003511751],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003395213,"threshold_uncertainty_score":0.01135808,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08142263447052059,"score_gpt":0.3227335214040331,"score_spread":0.2413108869335125,"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."}}