{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/generalization-bounds/papers/2","list_of":"/task/generalization-bounds","task":"Generalization Bounds","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":2,"pages_in_order":7,"rows_per_page":100,"rows":[101,200],"of":686,"counts":{"archive_papers_tagged":686,"with_a_code_link":161,"where_syntology_ran_a_sample":55,"not_listed_spam_title":0,"listed":686,"listed_where_code_ran":55,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":45,"every_run_a_failure_of_syntologys_instrument":10,"listed_with_a_run_with_no_instrument_failure":45,"listed_every_run_a_failure_of_syntologys_instrument":10,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/generalization-bounds","prev":"/task/generalization-bounds","next":"/task/generalization-bounds/papers/3","papers":[{"url":"/paper/generalization-bounds-for-meta-learning-an","slug":"generalization-bounds-for-meta-learning-an","title":"Generalization Bounds For Meta-Learning: An Information-Theoretic Analysis","date":"2021-09-29","arxiv_id":"2109.14595","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/generalization-bounds-for-meta-learning-an#ran","syntology_url":"https://syntology.ai/paper/2109.14595","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.14595"}},"official":{"repos":["livreq/meta-sgld"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-stochastic-majority-votes-by","slug":"learning-stochastic-majority-votes-by","title":"Learning Stochastic Majority Votes by Minimizing a PAC-Bayes Generalization Bound","date":"2021-06-23","arxiv_id":"2106.12535","repositories_listed":1,"syntology":null},{"url":"/paper/learning-the-optimal-regularizer-for-inverse","slug":"learning-the-optimal-regularizer-for-inverse","title":"Learning the optimal Tikhonov regularizer for inverse problems","date":"2021-06-11","arxiv_id":"2106.06513","repositories_listed":1,"syntology":null},{"url":"/paper/heavy-tails-in-sgd-and-compressibility-of","slug":"heavy-tails-in-sgd-and-compressibility-of","title":"Heavy Tails in SGD and Compressibility of Overparametrized Neural Networks","date":"2021-06-07","arxiv_id":"2106.03795","repositories_listed":1,"syntology":null},{"url":"/paper/measuring-generalization-with-optimal","slug":"measuring-generalization-with-optimal","title":"Measuring Generalization with Optimal Transport","date":"2021-06-07","arxiv_id":"2106.03314","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/measuring-generalization-with-optimal#ran","syntology_url":"https://syntology.ai/paper/2106.03314","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.03314"}},"official":{"repos":["chingyaoc/kV-Margin"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/stability-and-generalization-of-stochastic","slug":"stability-and-generalization-of-stochastic","title":"Stability and Generalization of Stochastic Gradient Methods for Minimax Problems","date":"2021-05-08","arxiv_id":"2105.03793","repositories_listed":1,"syntology":null},{"url":"/paper/ratt-leveraging-unlabeled-data-to-guarantee","slug":"ratt-leveraging-unlabeled-data-to-guarantee","title":"RATT: Leveraging Unlabeled Data to Guarantee Generalization","date":"2021-05-01","arxiv_id":"2105.00303","repositories_listed":1,"syntology":{"n":16,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/ratt-leveraging-unlabeled-data-to-guarantee#ran","syntology_url":"https://syntology.ai/paper/2105.00303","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.00303"}},"official":{"repos":["acmi-lab/ratt_generalization_bound"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/self-bounding-majority-vote-learning","slug":"self-bounding-majority-vote-learning","title":"Self-Bounding Majority Vote Learning Algorithms by the Direct Minimization of a Tight PAC-Bayesian C-Bound","date":"2021-04-28","arxiv_id":"2104.13626","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/self-bounding-majority-vote-learning#ran","syntology_url":"https://syntology.ai/paper/2104.13626","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.13626"}},"official":{"repos":["paulviallard/ecml21-pb-cbound"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluation-of-complexity-measures-for-deep","slug":"evaluation-of-complexity-measures-for-deep","title":"Evaluation of Complexity Measures for Deep Learning Generalization in Medical Image Analysis","date":"2021-03-04","arxiv_id":"2103.03328","repositories_listed":1,"syntology":null},{"url":"/paper/consistent-sparse-deep-learning-theory-and","slug":"consistent-sparse-deep-learning-theory-and","title":"Consistent Sparse Deep Learning: Theory and Computation","date":"2021-02-25","arxiv_id":"2102.13229","repositories_listed":1,"syntology":null},{"url":"/paper/generalization-bounds-for-graph-convolutional","slug":"generalization-bounds-for-graph-convolutional","title":"Generalization bounds for graph convolutional neural networks via Rademacher complexity","date":"2021-02-20","arxiv_id":"2102.10234","repositories_listed":1,"syntology":null},{"url":"/paper/a-pac-bayes-analysis-of-adversarial","slug":"a-pac-bayes-analysis-of-adversarial","title":"A PAC-Bayes Analysis of Adversarial Robustness","date":"2021-02-19","arxiv_id":"2102.11069","repositories_listed":1,"syntology":null},{"url":"/paper/on-approximation-in-deep-convolutional","slug":"on-approximation-in-deep-convolutional","title":"Approximation and Learning with Deep Convolutional Models: a Kernel Perspective","date":"2021-02-19","arxiv_id":"2102.10032","repositories_listed":1,"syntology":null},{"url":"/paper/a-general-framework-for-the-derandomization","slug":"a-general-framework-for-the-derandomization","title":"A General Framework for the Practical Disintegration of PAC-Bayesian Bounds","date":"2021-02-17","arxiv_id":"2102.08649","repositories_listed":1,"syntology":null},{"url":"/paper/pac-bus-meta-learning-bounds-via-pac-bayes","slug":"pac-bus-meta-learning-bounds-via-pac-bayes","title":"Generalization Bounds for Meta-Learning via PAC-Bayes and Uniform Stability","date":"2021-02-12","arxiv_id":"2102.06589","repositories_listed":1,"syntology":null},{"url":"/paper/robustness-to-augmentations-as-a","slug":"robustness-to-augmentations-as-a","title":"Robustness to Augmentations as a Generalization metric","date":"2021-01-16","arxiv_id":"2101.06459","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/robustness-to-augmentations-as-a#ran","syntology_url":"https://syntology.ai/paper/2101.06459","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.06459"}},"official":{"repos":["sumukhaithal6/pgdl"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/robustness-privacy-and-generalization-of","slug":"robustness-privacy-and-generalization-of","title":"Robustness, Privacy, and Generalization of Adversarial Training","date":"2020-12-25","arxiv_id":"2012.13573","repositories_listed":1,"syntology":null},{"url":"/paper/a-pac-bayesian-perspective-on-structured","slug":"a-pac-bayesian-perspective-on-structured","title":"A PAC-Bayesian Perspective on Structured Prediction with Implicit Loss Embeddings","date":"2020-12-07","arxiv_id":"2012.03780","repositories_listed":1,"syntology":null},{"url":"/paper/adapting-neural-architectures-between-domains","slug":"adapting-neural-architectures-between-domains","title":"Adapting Neural Architectures Between Domains","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/importance-weight-estimation-and","slug":"importance-weight-estimation-and","title":"Importance Weight Estimation and Generalization in Domain Adaptation under Label Shift","date":"2020-11-29","arxiv_id":"2011.14251","repositories_listed":1,"syntology":null},{"url":"/paper/instance-based-generalization-in","slug":"instance-based-generalization-in","title":"Instance based Generalization in Reinforcement Learning","date":"2020-11-02","arxiv_id":"2011.01089","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":4,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":7,"phrase":"6 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/instance-based-generalization-in#ran","syntology_url":"https://syntology.ai/paper/2011.01089","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.01089"}},"official":{"repos":["MartinBertran/InstanceAgnosticPolicyEnsembles"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/in-search-of-robust-measures-of","slug":"in-search-of-robust-measures-of","title":"In Search of Robust Measures of Generalization","date":"2020-10-22","arxiv_id":"2010.11924","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/in-search-of-robust-measures-of#ran","syntology_url":"https://syntology.ai/paper/2010.11924","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.11924"}},"official":{"repos":["nitarshan/robust-generalization-measures"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/selective-classification-via-one-sided","slug":"selective-classification-via-one-sided","title":"Selective Classification via One-Sided Prediction","date":"2020-10-15","arxiv_id":"2010.07853","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/selective-classification-via-one-sided#ran","syntology_url":"https://syntology.ai/paper/2010.07853","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.07853"}},"official":{"repos":["anilkagak2/SelectiveClassification_One_Sided_Prediction"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/covariate-shift-adaptation-in-high","slug":"covariate-shift-adaptation-in-high","title":"Effective Sample Size, Dimensionality, and Generalization in Covariate Shift Adaptation","date":"2020-10-02","arxiv_id":"2010.01184","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/covariate-shift-adaptation-in-high#ran","syntology_url":"https://syntology.ai/paper/2010.01184","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.01184"}},"official":{"repos":["felipemaiapolo/infoselect"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/principles-and-algorithms-for-forecasting","slug":"principles-and-algorithms-for-forecasting","title":"Principles and Algorithms for Forecasting Groups of Time Series: Locality and Globality","date":"2020-08-02","arxiv_id":"2008.00444","repositories_listed":1,"syntology":null},{"url":"/paper/consistent-structured-prediction-with-max-min","slug":"consistent-structured-prediction-with-max-min","title":"Consistent Structured Prediction with Max-Min Margin Markov Networks","date":"2020-07-02","arxiv_id":"2007.01012","repositories_listed":1,"syntology":null},{"url":"/paper/debiased-contrastive-learning","slug":"debiased-contrastive-learning","title":"Debiased Contrastive Learning","date":"2020-07-01","arxiv_id":"2007.00224","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/debiased-contrastive-learning#ran","syntology_url":"https://syntology.ai/paper/2007.00224","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.00224"}},"official":{"repos":["chingyaoc/DCL"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/hausdorff-dimension-stochastic-differential","slug":"hausdorff-dimension-stochastic-differential","title":"Hausdorff Dimension, Heavy Tails, and Generalization in Neural Networks","date":"2020-06-16","arxiv_id":"2006.09313","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/hausdorff-dimension-stochastic-differential#ran","syntology_url":"https://syntology.ai/paper/2006.09313","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.09313"}},"official":{"repos":["umutsimsekli/Hausdorff-Dimension-and-Generalization"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-generalization-by-controlling-label","slug":"improving-generalization-by-controlling-label","title":"Improving Generalization by Controlling Label-Noise Information in Neural Network Weights","date":"2020-02-19","arxiv_id":"2002.07933","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/improving-generalization-by-controlling-label#ran","syntology_url":"https://syntology.ai/paper/2002.07933","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.07933"}},"official":{"repos":["hrayrhar/limit-label-memorization"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/implicit-bias-of-gradient-descent-for-wide","slug":"implicit-bias-of-gradient-descent-for-wide","title":"Implicit Bias of Gradient Descent for Wide Two-layer Neural Networks Trained with the Logistic Loss","date":"2020-02-11","arxiv_id":"2002.04486","repositories_listed":1,"syntology":null},{"url":"/paper/linear-predictor-on-linearly-generated-data","slug":"linear-predictor-on-linearly-generated-data","title":"Linear predictor on linearly-generated data with missing values: non consistency and solutions","date":"2020-02-03","arxiv_id":"2002.00658","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/linear-predictor-on-linearly-generated-data#ran","syntology_url":"https://syntology.ai/paper/2002.00658","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.00658"}},"official":{"repos":["marineLM/linear_predictor_missing"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-overlapping-representations-for-the","slug":"learning-overlapping-representations-for-the","title":"Learning Overlapping Representations for the Estimation of Individualized Treatment Effects","date":"2020-01-14","arxiv_id":"2001.04754","repositories_listed":1,"syntology":null},{"url":"/paper/feature-robustness-flatness-and-1","slug":"feature-robustness-flatness-and-1","title":"Relative Flatness and Generalization","date":"2020-01-03","arxiv_id":"2001.00939","repositories_listed":1,"syntology":null},{"url":"/paper/transfer-learning-via-minimizing-the","slug":"transfer-learning-via-minimizing-the","title":"Transfer Learning via Minimizing the Performance Gap Between Domains","date":"2019-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/an-application-of-multiple-instance-learning","slug":"an-application-of-multiple-instance-learning","title":"Simplified and Unified Analysis of Various Learning Problems by Reduction to Multiple-Instance Learning","date":"2019-11-14","arxiv_id":"1911.05999","repositories_listed":1,"syntology":null},{"url":"/paper/information-theoretic-generalization-bounds","slug":"information-theoretic-generalization-bounds","title":"Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates","date":"2019-11-06","arxiv_id":"1911.02151","repositories_listed":1,"syntology":null},{"url":"/paper/diametrical-risk-minimization-theory-and","slug":"diametrical-risk-minimization-theory-and","title":"Diametrical Risk Minimization: Theory and Computations","date":"2019-10-24","arxiv_id":"1910.10844","repositories_listed":1,"syntology":null},{"url":"/paper/improved-sample-complexities-for-deep","slug":"improved-sample-complexities-for-deep","title":"Improved Sample Complexities for Deep Networks and Robust Classification via an All-Layer Margin","date":"2019-10-09","arxiv_id":"1910.04284","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/improved-sample-complexities-for-deep#ran","syntology_url":"https://syntology.ai/paper/1910.04284","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.04284"}},"official":{"repos":["cwein3/all-layer-margin-opt"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/graphmix-regularized-training-of-graph-neural","slug":"graphmix-regularized-training-of-graph-neural","title":"GraphMix: Improved Training of GNNs for Semi-Supervised Learning","date":"2019-09-25","arxiv_id":"1909.11715","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-downstream-performance-of-compressed","slug":"on-the-downstream-performance-of-compressed","title":"On the Downstream Performance of Compressed Word Embeddings","date":"2019-09-03","arxiv_id":"1909.01264","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/on-the-downstream-performance-of-compressed#ran","syntology_url":"https://syntology.ai/paper/1909.01264","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.01264"}},"official":{"repos":["HazyResearch/smallfry"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/maximum-weighted-loss-discrepancy","slug":"maximum-weighted-loss-discrepancy","title":"Maximum Weighted Loss Discrepancy","date":"2019-06-08","arxiv_id":"1906.03518","repositories_listed":1,"syntology":null},{"url":"/paper/an-adaptive-nearest-neighbor-rule-for","slug":"an-adaptive-nearest-neighbor-rule-for","title":"An adaptive nearest neighbor rule for classification","date":"2019-05-29","arxiv_id":"1905.12717","repositories_listed":1,"syntology":null},{"url":"/paper/eliciting-and-enforcing-subjective-individual","slug":"eliciting-and-enforcing-subjective-individual","title":"An Algorithmic Framework for Fairness Elicitation","date":"2019-05-25","arxiv_id":"1905.10660","repositories_listed":1,"syntology":null},{"url":"/paper/dichotomize-and-generalize-pac-bayesian","slug":"dichotomize-and-generalize-pac-bayesian","title":"Dichotomize and Generalize: PAC-Bayesian Binary Activated Deep Neural Networks","date":"2019-05-24","arxiv_id":"1905.10259","repositories_listed":1,"syntology":null},{"url":"/paper/provable-guarantees-for-gradient-based-meta","slug":"provable-guarantees-for-gradient-based-meta","title":"Provable Guarantees for Gradient-Based Meta-Learning","date":"2019-02-27","arxiv_id":"1902.10644","repositories_listed":1,"syntology":null},{"url":"/paper/uniform-convergence-may-be-unable-to-explain","slug":"uniform-convergence-may-be-unable-to-explain","title":"Uniform convergence may be unable to explain generalization in deep learning","date":"2019-02-13","arxiv_id":"1902.04742","repositories_listed":1,"syntology":null},{"url":"/paper/deep-neural-networks-are-biased-towards","slug":"deep-neural-networks-are-biased-towards","title":"Random deep neural networks are biased towards simple functions","date":"2018-12-25","arxiv_id":"1812.10156","repositories_listed":1,"syntology":null},{"url":"/paper/sorting-out-lipschitz-function-approximation","slug":"sorting-out-lipschitz-function-approximation","title":"Sorting out Lipschitz function approximation","date":"2018-11-13","arxiv_id":"1811.05381","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sorting-out-lipschitz-function-approximation#ran","syntology_url":"https://syntology.ai/paper/1811.05381","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.05381"}},"official":null}},{"url":"/paper/pseudo-bayesian-learning-with-kernel-fourier","slug":"pseudo-bayesian-learning-with-kernel-fourier","title":"Pseudo-Bayesian Learning with Kernel Fourier Transform as Prior","date":"2018-10-30","arxiv_id":"1810.12683","repositories_listed":1,"syntology":null},{"url":"/paper/learning-gaussian-processes-by-minimizing-pac","slug":"learning-gaussian-processes-by-minimizing-pac","title":"Learning Gaussian Processes by Minimizing PAC-Bayesian Generalization Bounds","date":"2018-10-29","arxiv_id":"1810.12263","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/learning-gaussian-processes-by-minimizing-pac#ran","syntology_url":"https://syntology.ai/paper/1810.12263","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.12263"}},"official":{"repos":["boschresearch/PAC_GP"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/on-pac-bayesian-bounds-for-random-forests","slug":"on-pac-bayesian-bounds-for-random-forests","title":"On PAC-Bayesian Bounds for Random Forests","date":"2018-10-23","arxiv_id":"1810.09746","repositories_listed":1,"syntology":null},{"url":"/paper/on-breimans-dilemma-in-neural-networks-phase","slug":"on-breimans-dilemma-in-neural-networks-phase","title":"Rethinking Breiman's Dilemma in Neural Networks: Phase Transitions of Margin Dynamics","date":"2018-10-08","arxiv_id":"1810.03389","repositories_listed":1,"syntology":null},{"url":"/paper/escaping-the-curse-of-dimensionality-in","slug":"escaping-the-curse-of-dimensionality-in","title":"Escaping the Curse of Dimensionality in Similarity Learning: Efficient Frank-Wolfe Algorithm and Generalization Bounds","date":"2018-07-20","arxiv_id":"1807.07789","repositories_listed":1,"syntology":null},{"url":"/paper/non-vacuous-generalization-bounds-at-the","slug":"non-vacuous-generalization-bounds-at-the","title":"Non-Vacuous Generalization Bounds at the ImageNet Scale: A PAC-Bayesian Compression Approach","date":"2018-04-16","arxiv_id":"1804.05862","repositories_listed":1,"syntology":{"n":15,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":13,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/non-vacuous-generalization-bounds-at-the#ran","syntology_url":"https://syntology.ai/paper/1804.05862","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.05862"}},"official":{"repos":["wendazhou/nnet-compression-generalization"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":13,"ran_from_kinds":["official"]}}},{"url":"/paper/estimating-the-success-of-unsupervised-image","slug":"estimating-the-success-of-unsupervised-image","title":"Estimating the Success of Unsupervised Image to Image Translation","date":"2017-12-21","arxiv_id":"1712.07886","repositories_listed":1,"syntology":null},{"url":"/paper/regularization-via-mass-transportation","slug":"regularization-via-mass-transportation","title":"Regularization via Mass Transportation","date":"2017-10-27","arxiv_id":"1710.10016","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/regularization-via-mass-transportation#ran","syntology_url":"https://syntology.ai/paper/1710.10016","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.10016"}},"official":{"repos":["sorooshafiee/Regularization-via-Transportation"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/a-pac-bayesian-analysis-of-randomized","slug":"a-pac-bayesian-analysis-of-randomized","title":"A PAC-Bayesian Analysis of Randomized Learning with Application to Stochastic Gradient Descent","date":"2017-09-19","arxiv_id":"1709.06617","repositories_listed":1,"syntology":null},{"url":"/paper/model-powered-conditional-independence-test","slug":"model-powered-conditional-independence-test","title":"Model-Powered Conditional Independence Test","date":"2017-09-18","arxiv_id":"1709.06138","repositories_listed":1,"syntology":null},{"url":"/paper/group-invariance-stability-to-deformations","slug":"group-invariance-stability-to-deformations","title":"Group Invariance, Stability to Deformations, and Complexity of Deep Convolutional Representations","date":"2017-06-09","arxiv_id":"1706.03078","repositories_listed":1,"syntology":null},{"url":"/paper/towards-a-learning-theory-of-cause-effect","slug":"towards-a-learning-theory-of-cause-effect","title":"Towards a Learning Theory of Cause-Effect Inference","date":"2015-02-09","arxiv_id":"1502.02398","repositories_listed":1,"syntology":null},{"url":"/paper/generalization-bounds-for-learning-with","slug":"generalization-bounds-for-learning-with","title":"Generalization Bounds for Learning with Linear, Polygonal, Quadratic and Conic Side Knowledge","date":"2014-05-30","arxiv_id":"1405.7764","repositories_listed":1,"syntology":null},{"url":null,"slug":"information-theoretic-generalization-bounds-9","title":"Information-Theoretic Generalization Bounds of Replay-based Continual Learning","date":"2025-07-16","arxiv_id":"2507.12043","repositories_listed":0,"syntology":null},{"url":null,"slug":"tuning-without-peeking-provable-privacy-and","title":"Tuning without Peeking: Provable Privacy and Generalization Bounds for LLM Post-Training","date":"2025-07-02","arxiv_id":"2507.01752","repositories_listed":0,"syntology":null},{"url":null,"slug":"tight-generalization-error-bounds-for","title":"Tight Generalization Error Bounds for Stochastic Gradient Descent in Non-convex Learning","date":"2025-06-23","arxiv_id":"2506.18645","repositories_listed":0,"syntology":null},{"url":null,"slug":"sharp-generalization-bounds-for-foundation","title":"Sharp Generalization Bounds for Foundation Models with Asymmetric Randomized Low-Rank Adapters","date":"2025-06-17","arxiv_id":"2506.14530","repositories_listed":0,"syntology":null},{"url":null,"slug":"stability-analysis-of-physics-informed-neural-1","title":"Stability Analysis of Physics-Informed Neural Networks via Variational Coercivity, Perturbation Bounds, and Concentration Estimates","date":"2025-06-16","arxiv_id":"2506.13554","repositories_listed":0,"syntology":null},{"url":null,"slug":"fairness-overfitting-in-machine-learning-an","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","date":"2025-06-09","arxiv_id":"2506.07861","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-drift-estimation-for-ergodic","title":"Neural Drift Estimation for Ergodic Diffusions: Non-parametric Analysis and Numerical Exploration","date":"2025-05-30","arxiv_id":"2505.24383","repositories_listed":0,"syntology":null},{"url":null,"slug":"epistemic-errors-of-imperfect-multitask","title":"Epistemic Errors of Imperfect Multitask Learners When Distributions Shift","date":"2025-05-29","arxiv_id":"2505.23496","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-rate-bounds-for-multi-task-and-meta","title":"Fast Rate Bounds for Multi-Task and Meta-Learning with Different Sample Sizes","date":"2025-05-21","arxiv_id":"2505.15496","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalization-through-growth-hidden-dynamics","title":"Generalization Through Growth: Hidden Dynamics Controls Depth Dependence","date":"2025-05-21","arxiv_id":"2505.15064","repositories_listed":0,"syntology":null},{"url":null,"slug":"2505-11025","title":"Generalization Bounds for Quantum Learning via Rényi Divergences","date":"2025-05-16","arxiv_id":"2505.11025","repositories_listed":0,"syntology":null},{"url":null,"slug":"2505-11360","title":"Efficient End-to-End Learning for Decision-Making: A Meta-Optimization Approach","date":"2025-05-16","arxiv_id":"2505.11360","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalization-bounds-and-stopping-rules-for","title":"Generalization Bounds and Stopping Rules for Learning with Self-Selected Data","date":"2025-05-12","arxiv_id":"2505.07367","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalization-analysis-for-contrastive-1","title":"Generalization Analysis for Contrastive Representation Learning under Non-IID Settings","date":"2025-05-08","arxiv_id":"2505.04937","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalization-guarantees-for-multi-view","title":"Generalization Guarantees for Multi-View Representation Learning and Application to Regularization via Gaussian Product Mixture Prior","date":"2025-04-25","arxiv_id":"2504.18455","repositories_listed":0,"syntology":null},{"url":null,"slug":"compute-optimal-llms-provably-generalize","title":"Compute-Optimal LLMs Provably Generalize Better With Scale","date":"2025-04-21","arxiv_id":"2504.15208","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalization-bounds-in-hybrid-quantum","title":"Generalization Bounds in Hybrid Quantum-Classical Machine Learning Models","date":"2025-04-11","arxiv_id":"2504.08456","repositories_listed":0,"syntology":null},{"url":null,"slug":"architecture-independent-generalization","title":"Architecture independent generalization bounds for overparametrized deep ReLU networks","date":"2025-04-08","arxiv_id":"2504.05695","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-equivariant-networks-with","title":"Improving Equivariant Networks with Probabilistic Symmetry Breaking","date":"2025-03-27","arxiv_id":"2503.21985","repositories_listed":0,"syntology":null},{"url":null,"slug":"non-vacuous-generalization-bounds-for-deep","title":"Non-vacuous Generalization Bounds for Deep Neural Networks without any modification to the trained models","date":"2025-03-10","arxiv_id":"2503.07325","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalizability-of-neural-networks","title":"Generalizability of Neural Networks Minimizing Empirical Risk Based on Expressive Ability","date":"2025-03-06","arxiv_id":"2503.04111","repositories_listed":0,"syntology":null},{"url":null,"slug":"stability-based-generalization-analysis-of","title":"Stability-based Generalization Analysis of Randomized Coordinate Descent for Pairwise Learning","date":"2025-03-03","arxiv_id":"2503.01530","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalization-bounds-for-equivariant","title":"Generalization Bounds for Equivariant Networks on Markov Data","date":"2025-03-01","arxiv_id":"2503.00292","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-auto-regressive-next-token-prediction","title":"Towards Auto-Regressive Next-Token Prediction: In-Context Learning Emerges from Generalization","date":"2025-02-24","arxiv_id":"2502.17024","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-margin-generalization-bounds-for","title":"Improved Margin Generalization Bounds for Voting Classifiers","date":"2025-02-23","arxiv_id":"2502.16462","repositories_listed":0,"syntology":null},{"url":null,"slug":"tight-generalization-bounds-for-large-margin","title":"Tight Generalization Bounds for Large-Margin Halfspaces","date":"2025-02-19","arxiv_id":"2502.13692","repositories_listed":0,"syntology":null},{"url":null,"slug":"sewa-selective-weight-average-via","title":"SeWA: Selective Weight Average via Probabilistic Masking","date":"2025-02-14","arxiv_id":"2502.10119","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-law-for-stochastic-gradient-descent","title":"Scaling Law for Stochastic Gradient Descent in Quadratically Parameterized Linear Regression","date":"2025-02-13","arxiv_id":"2502.09106","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-the-generalization-error-of","title":"Understanding the Generalization Error of Markov algorithms through Poissonization","date":"2025-02-11","arxiv_id":"2502.07584","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-driven-neural-certificate-synthesis","title":"Data-Driven Neural Certificate Synthesis","date":"2025-02-08","arxiv_id":"2502.05510","repositories_listed":0,"syntology":null},{"url":null,"slug":"algorithmic-stability-of-stochastic-gradient","title":"Algorithmic Stability of Stochastic Gradient Descent with Momentum under Heavy-Tailed Noise","date":"2025-02-02","arxiv_id":"2502.00885","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-the-generalization-of-multi-view","title":"Towards the Generalization of Multi-view Learning: An Information-theoretical Analysis","date":"2025-01-28","arxiv_id":"2501.16768","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-sharper-information-theoretic","title":"Towards Sharper Information-theoretic Generalization Bounds for Meta-Learning","date":"2025-01-26","arxiv_id":"2501.15559","repositories_listed":0,"syntology":null},{"url":null,"slug":"stability-and-generalization-of-quantum","title":"Stability and Generalization of Quantum Neural Networks","date":"2025-01-22","arxiv_id":"2501.12737","repositories_listed":0,"syntology":null},{"url":null,"slug":"explainable-neural-networks-with-guarantees-a","title":"Explainable Neural Networks with Guarantees: A Sparse Estimation Approach","date":"2025-01-02","arxiv_id":"2501.02010","repositories_listed":0,"syntology":null},{"url":null,"slug":"regularized-proportional-fairness-mechanism","title":"Regularized Proportional Fairness Mechanism for Resource Allocation Without Money","date":"2025-01-02","arxiv_id":"2501.01111","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-difficult-to-learn-examples-in","title":"Understanding Difficult-to-learn Examples in Contrastive Learning: A Theoretical Framework for Spectral Contrastive Learning","date":"2025-01-02","arxiv_id":"2501.01317","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-dependent-generalization-bounds-for-1","title":"Data-Dependent Generalization Bounds for Parameterized Quantum Models Under Noise","date":"2024-12-16","arxiv_id":"2412.11451","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalization-analysis-for-deep-contrastive","title":"Generalization Analysis for Deep Contrastive Representation Learning","date":"2024-12-16","arxiv_id":"2412.12014","repositories_listed":0,"syntology":null}],"record_sha256":"15be018fa29bb2f6a131918f9458c465fb804e724f017cd14a802ae890bcb179","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}