{"id":"W2912745458","doi":"10.1137/19m130858x","title":"Dual Space Preconditioning for Gradient Descent","year":2021,"lang":"en","type":"preprint","venue":"SIAM Journal on Optimization","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Army Research Laboratory; Army Research Office; Engineering and Physical Sciences Research Council; Ministry of Defence; Natural Sciences and Engineering Research Council of Canada; European Commission; Institute for Advanced Studies in the Humanities, University of Edinburgh; DeepMind; Seventh Framework Programme","keywords":"Convexity; Lipschitz continuity; Mathematics; Smoothness; Stochastic gradient descent; Gradient descent; Applied mathematics; Convex function; Gradient method; Nonlinear conjugate gradient method; Bregman divergence; Norm (philosophy); Proximal Gradient Methods; Mathematical analysis; Mathematical optimization; Regular polygon; Computer science; Geometry","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":[0.001034802,0.0008191328,0.0008250181,0.0005108307,0.0004798355,0.0009081197,0.0006051853,0.0009143467,0.005052785],"category_scores_gemma":[0.004092924,0.0003479508,0.0005779281,0.0005241585,0.001276678,0.001043176,0.002138655,0.002467028,0.001531839],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005620768,"about_ca_system_score_gemma":0.001096192,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001143478,"about_ca_topic_score_gemma":0.001385714,"domain_scores_codex":[0.9992824,0.0002613782,0.00003017699,0.00009922114,0.000257638,0.00006924757],"domain_scores_gemma":[0.9991807,0.0002617252,0.00007396415,0.0001978272,0.0002093309,0.00007641865],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002750441,0.00009395497,0.000699453,0.0002968696,0.00006595174,0.0002397411,0.0002085948,0.2550195,0.03477192,0.5544465,0.01035254,0.1435299],"study_design_scores_gemma":[0.00002527362,0.00005714819,0.0001397945,0.00002208592,0.000007482135,0.00006885773,0.0000141463,0.9226864,0.007249345,0.0615325,0.008182159,0.00001475745],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00275181,0.00008777287,0.9943817,0.00012782,0.00005149739,0.00001967407,0.00003246444,0.0001839581,0.002363252],"genre_scores_gemma":[0.2416906,0.000509805,0.7435734,0.0004539288,0.0002297564,0.0003166529,0.0003287326,0.0006419469,0.01225519],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005052785,"threshold_uncertainty_score":0.01690322,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02090318359265479,"score_gpt":0.2435101790497992,"score_spread":0.2226069954571444,"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."}}