{"id":"W4394867770","doi":"10.48550/arxiv.2404.09101","title":"Mixtures of Neural Operators Reduce Active Complexity in Operator Learning","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; European Commission; Rice University; U.S. Department of Energy","keywords":"Curse of dimensionality; Mathematics; Operator (biology); Lipschitz continuity; Constraint (computer-aided design); Scaling; Artificial neural network; Rank (graph theory); Discrete mathematics; Linear operators; Pure mathematics; Applied mathematics; Combinatorics; Computer science; Mathematical analysis; Artificial intelligence","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":[0.002817488,0.0008652432,0.0008280953,0.0006640732,0.0005045662,0.002122129,0.001754431,0.001644516,0.003468041],"category_scores_gemma":[0.01984013,0.0006790028,0.001036913,0.000426925,0.002065556,0.008238583,0.004462549,0.002772941,0.0006403115],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001274953,"about_ca_system_score_gemma":0.0007831693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008041507,"about_ca_topic_score_gemma":0.0008913293,"domain_scores_codex":[0.9983208,0.0005029923,0.0001138169,0.0004111494,0.0005016667,0.0001496477],"domain_scores_gemma":[0.9872447,0.00868544,0.0009628132,0.001753442,0.0008276958,0.0005259805],"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":[0.0006186012,0.0001847156,0.002818827,0.0003082514,0.0000992369,0.0002227209,0.0005942752,0.3785935,0.02523942,0.4634152,0.001589834,0.1263154],"study_design_scores_gemma":[0.00001512127,0.0001327866,0.0003230854,0.00001231155,0.00001679624,0.00007361269,0.00003898237,0.9034644,0.004337369,0.09074889,0.0008219791,0.00001472206],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07763652,0.0002095976,0.9177904,0.0003623658,0.00002817329,0.0000482545,0.00004910853,0.0005492889,0.003326337],"genre_scores_gemma":[0.7172751,0.0002491279,0.2764833,0.0002548046,0.0001061699,0.0001402755,0.0001383941,0.0002730216,0.005079702],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003468041,"threshold_uncertainty_score":0.01490045,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1020028580396869,"score_gpt":0.229997832808494,"score_spread":0.1279949747688071,"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."}}