{"url":"/task/model-selection","name":"Model Selection","slug":"model-selection","description_markdown":"Given a set of candidate models, the goal of **Model Selection** is to select the model that best approximates the observed data and captures its underlying regularities. Model Selection criteria are defined such that they strike a balance between the goodness of fit, and the generalizability or complexity of the models.\n\n\n<span class=\"description-source\">Source: [Kernel-based Information Criterion ](https://arxiv.org/abs/1408.5810)</span>","categories":[{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":2050,"papers_with_code":658,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/image-caption-quality-dataset","name":"Image Caption Quality Dataset","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":658,"tagged_in_all":2050,"items":[{"url":"/paper/bertscore-evaluating-text-generation-with","title":"BERTScore: Evaluating Text Generation with BERT","date":"2019-04-21","arxiv_id":"1904.09675","repositories_listed":20,"syntology":{"n":76,"n_ran":44,"n_unverified":32,"n_pointer_only":33}},{"url":"/paper/in-search-of-lost-domain-generalization","title":"In Search of Lost Domain Generalization","date":"2020-07-02","arxiv_id":"2007.01434","repositories_listed":12,"syntology":{"n":7,"n_ran":3,"n_unverified":4,"n_pointer_only":1}},{"url":"/paper/population-based-training-of-neural-networks","title":"Population Based Training of Neural Networks","date":"2017-11-27","arxiv_id":"1711.09846","repositories_listed":9,"syntology":null},{"url":"/paper/data-splits-and-metrics-for-method","title":"Data Splits and Metrics for Method Benchmarking on Surgical Action Triplet Datasets","date":"2022-04-11","arxiv_id":"2204.05235","repositories_listed":8,"syntology":null},{"url":"/paper/deep-domain-confusion-maximizing-for-domain","title":"Deep Domain Confusion: Maximizing for Domain Invariance","date":"2014-12-10","arxiv_id":"1412.3474","repositories_listed":7,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/laplace-redux-effortless-bayesian-deep","title":"Laplace Redux -- Effortless Bayesian Deep Learning","date":"2021-06-28","arxiv_id":"2106.14806","repositories_listed":6,"syntology":{"n":5,"n_ran":1,"n_unverified":4,"n_pointer_only":1}},{"url":"/paper/metric-learn-metric-learning-algorithms-in","title":"metric-learn: Metric Learning Algorithms in Python","date":"2019-08-13","arxiv_id":"1908.04710","repositories_listed":6,"syntology":null},{"url":"/paper/conditional-density-estimation-tools-in","title":"Conditional Density Estimation Tools in Python and R with Applications to Photometric Redshifts and Likelihood-Free Cosmological Inference","date":"2019-08-30","arxiv_id":"1908.11523","repositories_listed":5,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/barcodebert-transformers-for-biodiversity","title":"BarcodeBERT: Transformers for Biodiversity Analysis","date":"2023-11-04","arxiv_id":"2311.02401","repositories_listed":4,"syntology":{"n":16,"n_ran":12,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/testing-conditional-predictive-independence","title":"Testing Conditional Independence in Supervised Learning Algorithms","date":"2019-01-28","arxiv_id":"1901.09917","repositories_listed":4,"syntology":null},{"url":"/paper/model-evaluation-model-selection-and","title":"Model Evaluation, Model Selection, and Algorithm Selection in Machine Learning","date":"2018-11-13","arxiv_id":"1811.12808","repositories_listed":4,"syntology":null},{"url":"/paper/variational-bayesian-monte-carlo","title":"Variational Bayesian Monte Carlo","date":"2018-10-12","arxiv_id":"1810.05558","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/tune-a-research-platform-for-distributed","title":"Tune: A Research Platform for Distributed Model Selection and Training","date":"2018-07-13","arxiv_id":"1807.05118","repositories_listed":4,"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":9}},{"url":"/paper/learning-sparse-neural-networks-through-l_0","title":"Learning Sparse Neural Networks through $L_0$ Regularization","date":"2017-12-04","arxiv_id":"1712.01312","repositories_listed":4,"syntology":null},{"url":"/paper/neural-vector-spaces-for-unsupervised","title":"Neural Vector Spaces for Unsupervised Information Retrieval","date":"2017-08-09","arxiv_id":"1708.02702","repositories_listed":4,"syntology":null},{"url":"/paper/encoder-vs-decoder-comparative-analysis-of","title":"Encoder vs Decoder: Comparative Analysis of Encoder and Decoder Language Models on Multilingual NLU Tasks","date":"2024-06-19","arxiv_id":"2406.13469","repositories_listed":3,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/the-future-of-cosmological-likelihood-based","title":"The future of cosmological likelihood-based inference: accelerated high-dimensional parameter estimation and model comparison","date":"2024-05-21","arxiv_id":"2405.12965","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/a-deep-learning-method-for-comparing-bayesian","title":"A Deep Learning Method for Comparing Bayesian Hierarchical Models","date":"2023-01-27","arxiv_id":"2301.11873","repositories_listed":3,"syntology":null},{"url":"/paper/leather-a-framework-for-learning-to-generate","title":"LEATHER: A Framework for Learning to Generate Human-like Text in Dialogue","date":"2022-10-14","arxiv_id":"2210.07777","repositories_listed":3,"syntology":null},{"url":"/paper/volcanoml-speeding-up-end-to-end-automl-via","title":"VolcanoML: Speeding up End-to-End AutoML via Scalable Search Space Decomposition","date":"2021-07-19","arxiv_id":"2107.08861","repositories_listed":3,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/otce-a-transferability-metric-for-cross","title":"OTCE: A Transferability Metric for Cross-Domain Cross-Task Representations","date":"2021-03-25","arxiv_id":"2103.13843","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/cardea-an-open-automated-machine-learning","title":"Cardea: An Open Automated Machine Learning Framework for Electronic Health Records","date":"2020-10-01","arxiv_id":"2010.00509","repositories_listed":3,"syntology":null},{"url":"/paper/statistical-inference-of-minimally-complex","title":"Bayesian Inference of Minimally Complex Models with Interactions of Arbitrary Order","date":"2020-08-02","arxiv_id":"2008.00520","repositories_listed":3,"syntology":null},{"url":"/paper/automatic-catalog-of-rrlyrae-from-sim-14","title":"Automatic Catalog of RRLyrae from $\\sim$ 14 million VVV Light Curves: How far can we go with traditional machine-learning?","date":"2020-05-01","arxiv_id":"2005.00220","repositories_listed":3,"syntology":null},{"url":"/paper/deep-learning-algorithms-for-rotating","title":"Deep Learning Algorithms for Rotating Machinery Intelligent Diagnosis: An Open Source Benchmark Study","date":"2020-03-06","arxiv_id":"2003.03315","repositories_listed":3,"syntology":null},{"url":"/paper/predictive-multiplicity-in-classification","title":"Predictive Multiplicity in Classification","date":"2019-09-14","arxiv_id":"1909.06677","repositories_listed":3,"syntology":null},{"url":"/paper/interpretable-multiclass-classification-by","title":"Interpretable multiclass classification by MDL-based rule lists","date":"2019-05-01","arxiv_id":"1905.00328","repositories_listed":3,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/forecasting-with-time-series-imaging","title":"Forecasting with time series imaging","date":"2019-04-17","arxiv_id":"1904.08064","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/automatic-gradient-boosting","title":"Automatic Gradient Boosting","date":"2018-07-10","arxiv_id":"1807.03873","repositories_listed":3,"syntology":null},{"url":"/paper/a-comparison-of-methods-for-model-selection","title":"A comparison of methods for model selection when estimating individual treatment effects","date":"2018-04-14","arxiv_id":"1804.05146","repositories_listed":3,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}}],"syntology_records":15,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}