{"id":"W2969451120","doi":"","title":"A Lyapunov analysis for accelerated gradient methods: From deterministic to stochastic case","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Lyapunov function; Ode; Discretization; Mathematics; Applied mathematics; Ordinary differential equation; Stochastic gradient descent; Stochastic differential equation; Connection (principal bundle); Gradient descent; Acceleration; Convergence (economics); Mathematical analysis; Computer science; Differential equation; Nonlinear system; Physics","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":[0.0004511869,0.0005447525,0.0009023073,0.001445562,0.0002042677,0.0002901356,0.0021647,0.0003485006,0.00003625191],"category_scores_gemma":[0.0003326752,0.0006384572,0.0005422347,0.002516458,0.00006837297,0.0002356755,0.00206513,0.0003586535,0.00003964593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004202396,"about_ca_system_score_gemma":0.0002306186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004638981,"about_ca_topic_score_gemma":0.00008300879,"domain_scores_codex":[0.9964803,0.0002520759,0.000455954,0.002144128,0.0001252397,0.0005422599],"domain_scores_gemma":[0.995338,0.001028672,0.0004637289,0.002280855,0.0005129775,0.0003757277],"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":[0.00004737597,0.00008622416,0.0001337926,0.00003057555,0.0007573069,0.0004357357,0.0004668313,0.9739652,0.00002189254,0.02318819,0.00009371866,0.0007731278],"study_design_scores_gemma":[0.0004106188,0.0001499031,0.0001546431,0.00005812513,0.001218525,0.0000209704,0.000056948,0.9722925,0.000114443,0.02481886,0.00003183888,0.00067256],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03490209,0.00002363794,0.9616124,0.0000482561,0.0007858442,0.001711503,0.000232292,0.0005981984,0.00008575544],"genre_scores_gemma":[0.6822278,0.000003186413,0.3172649,0.0001126156,0.00003376729,0.00002331292,0.00007998543,0.00002781871,0.00022664],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6473257,"threshold_uncertainty_score":0.9996067,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1541293982343672,"score_gpt":0.273139175307576,"score_spread":0.1190097770732088,"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."}}