{"id":"W4287644884","doi":"10.48550/arxiv.2010.03533","title":"Gradient Flow in Sparse Neural Networks and How Lottery Tickets Win","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Initialization; Computer science; Generalization; Pruning; Artificial intelligence; Inference; Artificial neural network; Flow (mathematics); Machine learning; Balanced flow; Sparse matrix; Lottery; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00208434,0.0004039507,0.00107417,0.0006573551,0.0008102924,0.002352386,0.001068255,0.002066195,0.01021088],"category_scores_gemma":[0.01856876,0.0004921606,0.0005840284,0.0007008187,0.00181892,0.005157585,0.001044114,0.002797775,0.0007097762],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001447448,"about_ca_system_score_gemma":0.0007753278,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003065529,"about_ca_topic_score_gemma":0.003346561,"domain_scores_codex":[0.9993704,0.000321525,0.00002270564,0.0001234141,0.00007892433,0.0000830781],"domain_scores_gemma":[0.9962817,0.002707549,0.0002935521,0.0002046022,0.0002280002,0.0002845619],"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":[0.0004251545,0.0001240558,0.002184326,0.0001302258,0.000105358,0.00008499416,0.0002794622,0.1396745,0.001163792,0.7699043,0.01965332,0.06627049],"study_design_scores_gemma":[0.00002745725,0.00002930809,0.000589711,0.00001907858,0.00001697123,0.000025533,0.00008389101,0.3332853,0.0003380727,0.6638262,0.001740144,0.0000184127],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3371384,0.003595953,0.5964072,0.02018729,0.0009124036,0.0001026792,0.0007484855,0.0007414132,0.04016617],"genre_scores_gemma":[0.9478368,0.0006797623,0.02968865,0.0005578621,0.0002166359,0.00006422748,0.000226293,0.0002062857,0.02052354],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01021088,"threshold_uncertainty_score":0.03415877,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08419623647118654,"score_gpt":0.1781086397888582,"score_spread":0.09391240331767167,"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."}}