{"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/quantifying-uncertainty-in-discrete","title":"Quantifying Uncertainty in Discrete-Continuous and Skewed Data with Bayesian Deep Learning","arxiv_id":"1802.04742","date":"2018-02-13","proceeding":null,"authors":["Thomas Vandal","Evan Kodra","Jennifer Dy","Sangram Ganguly","Ramakrishna Nemani","Auroop R. Ganguly"],"abstract":"Deep Learning (DL) methods have been transforming computer vision with\ninnovative adaptations to other domains including climate change. For DL to\npervade Science and Engineering (S&E) applications where risk management is a\ncore component, well-characterized uncertainty estimates must accompany\npredictions. However, S&E observations and model-simulations often follow\nheavily skewed distributions and are not well modeled with DL approaches, since\nthey usually optimize a Gaussian, or Euclidean, likelihood loss. Recent\ndevelopments in Bayesian Deep Learning (BDL), which attempts to capture\nuncertainties from noisy observations, aleatoric, and from unknown model\nparameters, epistemic, provide us a foundation. Here we present a\ndiscrete-continuous BDL model with Gaussian and lognormal likelihoods for\nuncertainty quantification (UQ). We demonstrate the approach by developing UQ\nestimates on `DeepSD', a super-resolution based DL model for Statistical\nDownscaling (SD) in climate applied to precipitation, which follows an\nextremely skewed distribution. We find that the discrete-continuous models\noutperform a basic Gaussian distribution in terms of predictive accuracy and\nuncertainty calibration. Furthermore, we find that the lognormal distribution,\nwhich can handle skewed distributions, produces quality uncertainty estimates\nat the extremes. Such results may be important across S&E, as well as other\ndomains such as finance and economics, where extremes are often of significant\ninterest. Furthermore, to our knowledge, this is the first UQ model in SD where\nboth aleatoric and epistemic uncertainties are characterized.","url_abs":"http://arxiv.org/abs/1802.04742v2","url_pdf":"http://arxiv.org/pdf/1802.04742v2.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":[{"paper_slug":"quantifying-uncertainty-in-discrete","repo_url":"https://github.com/tjvandal/discrete-continuous-bdl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"management","task_name":"Management"},{"task_slug":"super-resolution","task_name":"Super-Resolution"},{"task_slug":"uncertainty-quantification","task_name":"Uncertainty Quantification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.04742","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.04742"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tjvandal/discrete-continuous-bdl","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"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":0,"samples":[{"code_sha256_prefix":"989a3abff4e2cc42","entry":"concrete_layer","repo":"tjvandal/discrete-continuous-bdl","repo_kind":"official","path":"bdl.py","file_url":"https://github.com/tjvandal/discrete-continuous-bdl/blob/HEAD/bdl.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"989a3abff4e2cc42"}},{"code_sha256_prefix":"90bc251762c54b28","entry":"fill_na","repo":"tjvandal/discrete-continuous-bdl","repo_kind":"official","path":"tf_utils.py","file_url":"https://github.com/tjvandal/discrete-continuous-bdl/blob/HEAD/tf_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"90bc251762c54b28"}},{"code_sha256_prefix":"d7b358161d9d8226","entry":"nanmean","repo":"tjvandal/discrete-continuous-bdl","repo_kind":"official","path":"tf_utils.py","file_url":"https://github.com/tjvandal/discrete-continuous-bdl/blob/HEAD/tf_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d7b358161d9d8226"}},{"code_sha256_prefix":"3829849a71fd99c7","entry":"read_and_decode","repo":"tjvandal/discrete-continuous-bdl","repo_kind":"official","path":"tf_utils.py","file_url":"https://github.com/tjvandal/discrete-continuous-bdl/blob/HEAD/tf_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3829849a71fd99c7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}