{"id":"W4286569388","doi":"10.1109/compel53829.2022.9829984","title":"Multi-Objective Optimization of EE-core Transformers using Geometric Programming","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Advanced Multi-Objective Optimization Algorithms","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Xerox (Canada)","funders":"","keywords":"Geometric programming; Mathematical optimization; Transformer; Monomial; Computer science; Multi-objective optimization; Pareto optimal; Optimality criterion; Mathematics; Engineering; Discrete mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004852694,0.0005411799,0.0006807104,0.001730571,0.0002962773,0.0001429887,0.001402145,0.0002800045,0.0002036359],"category_scores_gemma":[0.0002078474,0.0005825855,0.0003298977,0.003641025,0.0001281016,0.0007527532,0.001609537,0.0008493612,0.000002044753],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007837203,"about_ca_system_score_gemma":0.0005253226,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00024077,"about_ca_topic_score_gemma":0.00000871128,"domain_scores_codex":[0.9962834,0.0001464676,0.0008527245,0.001333797,0.0008402384,0.0005434166],"domain_scores_gemma":[0.9972546,0.0001613351,0.0008370375,0.0008492353,0.000744653,0.0001531324],"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":[0.00001084454,0.0002532128,0.0001500686,0.00009521993,0.0000959221,0.000008938447,0.0009082622,0.9554065,0.0000644524,0.0002253734,0.000002291522,0.04277894],"study_design_scores_gemma":[0.0008421205,0.00009696288,0.0001719706,0.00005208042,0.0000455899,0.00001508917,0.0004251431,0.9967498,0.000826526,0.00009597851,0.00008238901,0.0005963268],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003236111,0.0002474933,0.995288,0.00003753395,0.001062992,0.001852012,0.00004321488,0.0004476566,0.0006974786],"genre_scores_gemma":[0.01643033,0.0001256395,0.9827283,0.0000490756,0.00003874031,0.0001949978,0.00009569458,0.00007276562,0.0002644385],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04218261,"threshold_uncertainty_score":0.9996626,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05209947153646424,"score_gpt":0.3188917139238718,"score_spread":0.2667922423874076,"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."}}