{"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/simple-and-principled-uncertainty-estimation","title":"Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness","arxiv_id":"2006.10108","date":"2020-06-17","proceeding":"NeurIPS 2020 12","authors":["Jeremiah Zhe Liu","Zi Lin","Shreyas Padhy","Dustin Tran","Tania Bedrax-Weiss","Balaji Lakshminarayanan"],"abstract":"Bayesian neural networks (BNN) and deep ensembles are principled approaches to estimate the predictive uncertainty of a deep learning model. However their practicality in real-time, industrial-scale applications are limited due to their heavy memory and inference cost. This motivates us to study principled approaches to high-quality uncertainty estimation that require only a single deep neural network (DNN). By formalizing the uncertainty quantification as a minimax learning problem, we first identify input distance awareness, i.e., the model's ability to quantify the distance of a testing example from the training data in the input space, as a necessary condition for a DNN to achieve high-quality (i.e., minimax optimal) uncertainty estimation. We then propose Spectral-normalized Neural Gaussian Process (SNGP), a simple method that improves the distance-awareness ability of modern DNNs, by adding a weight normalization step during training and replacing the output layer with a Gaussian process. On a suite of vision and language understanding tasks and on modern architectures (Wide-ResNet and BERT), SNGP is competitive with deep ensembles in prediction, calibration and out-of-domain detection, and outperforms the other single-model approaches.","url_abs":"https://arxiv.org/abs/2006.10108v2","url_pdf":"https://arxiv.org/pdf/2006.10108v2.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":"simple-and-principled-uncertainty-estimation","repo_url":"https://github.com/google/uncertainty-baselines","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"simple-and-principled-uncertainty-estimation","repo_url":"https://github.com/vtekur/DeepUncertaintyEstimation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"simple-and-principled-uncertainty-estimation","repo_url":"https://github.com/y0ast/DUE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"simple-and-principled-uncertainty-estimation","repo_url":"https://github.com/lightning-uq-box/lightning-uq-box","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"uncertainty-quantification","task_name":"Uncertainty Quantification"}],"methods":[{"method_slug":"deep-ensembles","method_name":"Deep Ensembles"},{"method_slug":"gaussian-process","method_name":"Gaussian Process"},{"method_slug":"weight-normalization","method_name":"Weight Normalization"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.10108","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.10108"}},"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/google/uncertainty-baselines","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vtekur/DeepUncertaintyEstimation","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lightning-uq-box/lightning-uq-box","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/y0ast/DUE","reach":null}],"summary":{"ran_draft_wrong":1,"ran_honours":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":1,"ran":1,"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":"99f43556cdbc9564","entry":"get_sweep","repo":"google/uncertainty-baselines","repo_kind":"official","path":"baselines/cifar/experiments/sngp_tune.py","file_url":"https://github.com/google/uncertainty-baselines/blob/HEAD/baselines/cifar/experiments/sngp_tune.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"99f43556cdbc9564"}},{"code_sha256_prefix":"23d31486a37ba535","entry":"random_ortho","repo":"y0ast/DUE","repo_kind":"listed","path":"due/sngp.py","file_url":"https://github.com/y0ast/DUE/blob/HEAD/due/sngp.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"23d31486a37ba535"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}