{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/robust-gaussian-processes-via-relevance","title":"Robust Gaussian Processes via Relevance Pursuit","arxiv_id":"2410.24222","date":"2024-10-31","proceeding":null,"authors":["Sebastian Ament","Elizabeth Santorella","David Eriksson","Ben Letham","Maximilian Balandat","Eytan Bakshy"],"abstract":"Gaussian processes (GPs) are non-parametric probabilistic regression models that are popular due to their flexibility, data efficiency, and well-calibrated uncertainty estimates. However, standard GP models assume homoskedastic Gaussian noise, while many real-world applications are subject to non-Gaussian corruptions. Variants of GPs that are more robust to alternative noise models have been proposed, and entail significant trade-offs between accuracy and robustness, and between computational requirements and theoretical guarantees. In this work, we propose and study a GP model that achieves robustness against sparse outliers by inferring data-point-specific noise levels with a sequential selection procedure maximizing the log marginal likelihood that we refer to as relevance pursuit. We show, surprisingly, that the model can be parameterized such that the associated log marginal likelihood is strongly concave in the data-point-specific noise variances, a property rarely found in either robust regression objectives or GP marginal likelihoods. This in turn implies the weak submodularity of the corresponding subset selection problem, and thereby proves approximation guarantees for the proposed algorithm. We compare the model's performance relative to other approaches on diverse regression and Bayesian optimization tasks, including the challenging but common setting of sparse corruptions of the labels within or close to the function range.","url_abs":"https://arxiv.org/abs/2410.24222v2","url_pdf":"https://arxiv.org/pdf/2410.24222v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"bayesian-optimization","task_name":"Bayesian Optimization"},{"task_slug":"gaussian-processes","task_name":"Gaussian Processes"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[{"method_slug":"gps","method_name":"GPS"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.24222","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.24222"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/andrade-stats/TrimmedMarginalLikelihoodGP","reach":null}],"summary":{"ran_draft_wrong":6,"ran":7,"ran_violates":1,"ran_honours":2,"ran_fixture":1,"unverified":9},"by_repo_kind":{"found_in_text":{"samples":26,"ran":17,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":26,"samples":[{"code_sha256_prefix":"d2cd91460bd9f7b1","entry":"COVARIANCE_FUNCTION","repo":"andrade-stats/TrimmedMarginalLikelihoodGP","repo_kind":"found_in_text","path":"trimmedGP.py","file_url":"https://github.com/andrade-stats/TrimmedMarginalLikelihoodGP/blob/HEAD/trimmedGP.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"d2cd91460bd9f7b1"}},{"code_sha256_prefix":"4c3525cb9ae83944","entry":"evalObjectiveFunction","repo":"andrade-stats/TrimmedMarginalLikelihoodGP","repo_kind":"found_in_text","path":"trimmedGP.py","file_url":"https://github.com/andrade-stats/TrimmedMarginalLikelihoodGP/blob/HEAD/trimmedGP.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"4c3525cb9ae83944"}},{"code_sha256_prefix":"448aa062840163cd","entry":"getInlierAndOutliersBasedOnMarginalLikelihood_hardthresholding","repo":"andrade-stats/TrimmedMarginalLikelihoodGP","repo_kind":"found_in_text","path":"trimmedGP.py","file_url":"https://github.com/andrade-stats/TrimmedMarginalLikelihoodGP/blob/HEAD/trimmedGP.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"448aa062840163cd"}},{"code_sha256_prefix":"291dd8e1b906e90e","entry":"getLogPValues_fromSigmaEstimate_and_absValues","repo":"andrade-stats/TrimmedMarginalLikelihoodGP","repo_kind":"found_in_text","path":"trimmedGP.py","file_url":"https://github.com/andrade-stats/TrimmedMarginalLikelihoodGP/blob/HEAD/trimmedGP.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"291dd8e1b906e90e"}},{"code_sha256_prefix":"d991eef4d3475a0a","entry":"getMarginalLogLikelihood_fromLogDetL_and_invK","repo":"andrade-stats/TrimmedMarginalLikelihoodGP","repo_kind":"found_in_text","path":"trimmedGP.py","file_url":"https://github.com/andrade-stats/TrimmedMarginalLikelihoodGP/blob/HEAD/trimmedGP.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"d991eef4d3475a0a"}},{"code_sha256_prefix":"0b47181a947ba565","entry":"getMeanPredictions","repo":"andrade-stats/TrimmedMarginalLikelihoodGP","repo_kind":"found_in_text","path":"trimmedGP.py","file_url":"https://github.com/andrade-stats/TrimmedMarginalLikelihoodGP/blob/HEAD/trimmedGP.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"0b47181a947ba565"}},{"code_sha256_prefix":"99dd0e885dedd225","entry":"getNumpyDet","repo":"andrade-stats/TrimmedMarginalLikelihoodGP","repo_kind":"found_in_text","path":"trimmedGP.py","file_url":"https://github.com/andrade-stats/TrimmedMarginalLikelihoodGP/blob/HEAD/trimmedGP.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"99dd0e885dedd225"}},{"code_sha256_prefix":"a5d23e9cec06fbaf","entry":"getPredictions","repo":"andrade-stats/TrimmedMarginalLikelihoodGP","repo_kind":"found_in_text","path":"trimmedGP.py","file_url":"https://github.com/andrade-stats/TrimmedMarginalLikelihoodGP/blob/HEAD/trimmedGP.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"a5d23e9cec06fbaf"}},{"code_sha256_prefix":"86df8413ca1c1181","entry":"getTorchTensor","repo":"andrade-stats/TrimmedMarginalLikelihoodGP","repo_kind":"found_in_text","path":"trimmedGP.py","file_url":"https://github.com/andrade-stats/TrimmedMarginalLikelihoodGP/blob/HEAD/trimmedGP.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"86df8413ca1c1181"}},{"code_sha256_prefix":"946645cc1e652efe","entry":"mean_standardized_log_loss","repo":"andrade-stats/TrimmedMarginalLikelihoodGP","repo_kind":"found_in_text","path":"trimmedGP.py","file_url":"https://github.com/andrade-stats/TrimmedMarginalLikelihoodGP/blob/HEAD/trimmedGP.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"946645cc1e652efe"}},{"code_sha256_prefix":"f7b2a5ca26e674d4","entry":"median_absolute_error","repo":"andrade-stats/TrimmedMarginalLikelihoodGP","repo_kind":"found_in_text","path":"trimmedGP.py","file_url":"https://github.com/andrade-stats/TrimmedMarginalLikelihoodGP/blob/HEAD/trimmedGP.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"f7b2a5ca26e674d4"}},{"code_sha256_prefix":"da369a0ea11acfa1","entry":"negative_log_predictive_density","repo":"andrade-stats/TrimmedMarginalLikelihoodGP","repo_kind":"found_in_text","path":"trimmedGP.py","file_url":"https://github.com/andrade-stats/TrimmedMarginalLikelihoodGP/blob/HEAD/trimmedGP.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"da369a0ea11acfa1"}},{"code_sha256_prefix":"ff86313999ae79a3","entry":"project_b","repo":"andrade-stats/TrimmedMarginalLikelihoodGP","repo_kind":"found_in_text","path":"trimmedGP.py","file_url":"https://github.com/andrade-stats/TrimmedMarginalLikelihoodGP/blob/HEAD/trimmedGP.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"ff86313999ae79a3"}},{"code_sha256_prefix":"a13c53202405f060","entry":"root_mean_squared_error","repo":"andrade-stats/TrimmedMarginalLikelihoodGP","repo_kind":"found_in_text","path":"trimmedGP.py","file_url":"https://github.com/andrade-stats/TrimmedMarginalLikelihoodGP/blob/HEAD/trimmedGP.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"a13c53202405f060"}},{"code_sha256_prefix":"87eaafe54e24c911","entry":"setDataType","repo":"andrade-stats/TrimmedMarginalLikelihoodGP","repo_kind":"found_in_text","path":"trimmedGP.py","file_url":"https://github.com/andrade-stats/TrimmedMarginalLikelihoodGP/blob/HEAD/trimmedGP.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"87eaafe54e24c911"}},{"code_sha256_prefix":"799d79416d288b43","entry":"setSigma","repo":"andrade-stats/TrimmedMarginalLikelihoodGP","repo_kind":"found_in_text","path":"trimmedGP.py","file_url":"https://github.com/andrade-stats/TrimmedMarginalLikelihoodGP/blob/HEAD/trimmedGP.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"799d79416d288b43"}},{"code_sha256_prefix":"4459709d201b16c7","entry":"set_new_data_and_get_loss","repo":"andrade-stats/TrimmedMarginalLikelihoodGP","repo_kind":"found_in_text","path":"trimmedGP.py","file_url":"https://github.com/andrade-stats/TrimmedMarginalLikelihoodGP/blob/HEAD/trimmedGP.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"4459709d201b16c7"}},{"code_sha256_prefix":"a255e6bf79d3626b","entry":"BasicGP","repo":"andrade-stats/TrimmedMarginalLikelihoodGP","repo_kind":"found_in_text","path":"trimmedGP.py","file_url":"https://github.com/andrade-stats/TrimmedMarginalLikelihoodGP/blob/HEAD/trimmedGP.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"a255e6bf79d3626b"}},{"code_sha256_prefix":"8237f76c5e519459","entry":"ExactGPModel","repo":"andrade-stats/TrimmedMarginalLikelihoodGP","repo_kind":"found_in_text","path":"trimmedGP.py","file_url":"https://github.com/andrade-stats/TrimmedMarginalLikelihoodGP/blob/HEAD/trimmedGP.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"8237f76c5e519459"}},{"code_sha256_prefix":"08a889a7dc6ba985","entry":"assertOnDevice","repo":"andrade-stats/TrimmedMarginalLikelihoodGP","repo_kind":"found_in_text","path":"trimmedGP.py","file_url":"https://github.com/andrade-stats/TrimmedMarginalLikelihoodGP/blob/HEAD/trimmedGP.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"08a889a7dc6ba985"}},{"code_sha256_prefix":"b2969362affc8d48","entry":"calculateAllMLL_oneRemoved","repo":"andrade-stats/TrimmedMarginalLikelihoodGP","repo_kind":"found_in_text","path":"trimmedGP.py","file_url":"https://github.com/andrade-stats/TrimmedMarginalLikelihoodGP/blob/HEAD/trimmedGP.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"b2969362affc8d48"}},{"code_sha256_prefix":"0ed2f438f56e0ab0","entry":"getInlierAndOutliersBasedOnMarginalLikelihood_greedy","repo":"andrade-stats/TrimmedMarginalLikelihoodGP","repo_kind":"found_in_text","path":"trimmedGP.py","file_url":"https://github.com/andrade-stats/TrimmedMarginalLikelihoodGP/blob/HEAD/trimmedGP.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"0ed2f438f56e0ab0"}},{"code_sha256_prefix":"3b9b9f2c25f04e82","entry":"greedyMaximizeMLL_RemoveBatch","repo":"andrade-stats/TrimmedMarginalLikelihoodGP","repo_kind":"found_in_text","path":"trimmedGP.py","file_url":"https://github.com/andrade-stats/TrimmedMarginalLikelihoodGP/blob/HEAD/trimmedGP.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"3b9b9f2c25f04e82"}},{"code_sha256_prefix":"5a264b3cf0728c53","entry":"greedyMaximizeMLL_RemoveOneByOne","repo":"andrade-stats/TrimmedMarginalLikelihoodGP","repo_kind":"found_in_text","path":"trimmedGP.py","file_url":"https://github.com/andrade-stats/TrimmedMarginalLikelihoodGP/blob/HEAD/trimmedGP.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"5a264b3cf0728c53"}},{"code_sha256_prefix":"cbe4ecbe2e4d098f","entry":"showProgressGP","repo":"andrade-stats/TrimmedMarginalLikelihoodGP","repo_kind":"found_in_text","path":"trimmedGP.py","file_url":"https://github.com/andrade-stats/TrimmedMarginalLikelihoodGP/blob/HEAD/trimmedGP.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"cbe4ecbe2e4d098f"}},{"code_sha256_prefix":"7a03cb273dab01a2","entry":"trainTrimmedGP","repo":"andrade-stats/TrimmedMarginalLikelihoodGP","repo_kind":"found_in_text","path":"trimmedGP.py","file_url":"https://github.com/andrade-stats/TrimmedMarginalLikelihoodGP/blob/HEAD/trimmedGP.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"7a03cb273dab01a2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}