{"id":"W4385571590","doi":"10.18653/v1/2023.findings-acl.180","title":"Operator Selection and Ordering in a Pipeline Approach to Efficiency Optimizations for Transformers","year":2023,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund","keywords":"Computer science; Commutative property; Pipeline (software); Operator (biology); Quantization (signal processing); Inference; Transformer; Theoretical computer science; Artificial intelligence; Algorithm; Mathematics; Programming language; Engineering","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":[0.006119433,0.00101913,0.001102152,0.001599967,0.001179269,0.002934789,0.002288575,0.000976998,0.008282468],"category_scores_gemma":[0.01413428,0.0007802061,0.001798165,0.001584618,0.003470956,0.008439256,0.004354443,0.003119313,0.001363823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002046748,"about_ca_system_score_gemma":0.00401641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00335014,"about_ca_topic_score_gemma":0.005325553,"domain_scores_codex":[0.9953917,0.001570983,0.0002911157,0.0006547954,0.001546948,0.0005444357],"domain_scores_gemma":[0.9926369,0.003688682,0.0003368284,0.002126141,0.0009557367,0.0002556646],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004115156,0.0002292485,0.001677442,0.0002805264,0.00006334952,0.0001718729,0.0006887864,0.07234523,0.01970915,0.6828931,0.006331208,0.2151986],"study_design_scores_gemma":[0.0000889499,0.0001512226,0.0003481294,0.00004474042,0.00005991591,0.0001395548,0.0001370112,0.4274741,0.01843205,0.5422946,0.01078781,0.00004190599],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01129866,0.0001354569,0.9835067,0.0003173048,0.00003464217,0.00008725533,0.0000678504,0.001365235,0.003186943],"genre_scores_gemma":[0.2604444,0.0002075622,0.7332266,0.0002889815,0.00006898833,0.0001744101,0.0001964807,0.001135637,0.004256923],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008282468,"threshold_uncertainty_score":0.032363,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01306476756127116,"score_gpt":0.263144824771561,"score_spread":0.2500800572102899,"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."}}