{"id":"W4392903228","doi":"10.1109/icassp48485.2024.10446522","title":"Revisiting the Equivalence of In-Context Learning and Gradient Descent: The Impact of Data Distribution","year":2024,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Gradient descent; Computer science; Equivalence (formal languages); Softmax function; Covariance; Algorithm; Artificial intelligence; Mathematics; Deep learning; Statistics; Discrete mathematics; Artificial neural network","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004767671,0.0008168147,0.001272262,0.0005146683,0.0007237094,0.002372288,0.002573053,0.001570941,0.004562056],"category_scores_gemma":[0.0374816,0.000704505,0.0006176269,0.0006555002,0.003315473,0.007201001,0.00531684,0.005040851,0.0008759893],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001290449,"about_ca_system_score_gemma":0.001470667,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003938902,"about_ca_topic_score_gemma":0.003109602,"domain_scores_codex":[0.9977236,0.001020719,0.00008381946,0.0006748533,0.0003062006,0.0001908152],"domain_scores_gemma":[0.9858154,0.009583226,0.0005266707,0.002984106,0.0006128165,0.0004776691],"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":[0.000823712,0.0004629988,0.007358832,0.0003927748,0.000153947,0.0003123519,0.001411048,0.2008588,0.01491511,0.4211801,0.005385536,0.3467448],"study_design_scores_gemma":[0.00004925624,0.0001855013,0.001221792,0.00004301736,0.00002358457,0.000141206,0.00008498743,0.7668895,0.004087544,0.225025,0.002222254,0.00002626348],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04377597,0.0005649659,0.9459755,0.001554808,0.00009417662,0.00008998213,0.00008935326,0.0008759866,0.006979303],"genre_scores_gemma":[0.8789701,0.000436987,0.1156191,0.000802235,0.0001532537,0.0001322885,0.0001422576,0.0004456993,0.003297986],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004767671,"threshold_uncertainty_score":0.02521414,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05397476545594782,"score_gpt":0.3352681495908358,"score_spread":0.281293384134888,"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."}}