{"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/packed-ensembles-for-efficient-uncertainty","title":"Packed-Ensembles for Efficient Uncertainty Estimation","arxiv_id":"2210.09184","date":"2022-10-17","proceeding":null,"authors":["Olivier Laurent","Adrien Lafage","Enzo Tartaglione","Geoffrey Daniel","Jean-Marc Martinez","Andrei Bursuc","Gianni Franchi"],"abstract":"Deep Ensembles (DE) are a prominent approach for achieving excellent performance on key metrics such as accuracy, calibration, uncertainty estimation, and out-of-distribution detection. However, hardware limitations of real-world systems constrain to smaller ensembles and lower-capacity networks, significantly deteriorating their performance and properties. We introduce Packed-Ensembles (PE), a strategy to design and train lightweight structured ensembles by carefully modulating the dimension of their encoding space. We leverage grouped convolutions to parallelize the ensemble into a single shared backbone and forward pass to improve training and inference speeds. PE is designed to operate within the memory limits of a standard neural network. Our extensive research indicates that PE accurately preserves the properties of DE, such as diversity, and performs equally well in terms of accuracy, calibration, out-of-distribution detection, and robustness to distribution shift. We make our code available at https://github.com/ENSTA-U2IS/torch-uncertainty.","url_abs":"https://arxiv.org/abs/2210.09184v3","url_pdf":"https://arxiv.org/pdf/2210.09184v3.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":"packed-ensembles-for-efficient-uncertainty","repo_url":"https://github.com/ENSTA-U2IS-AI/torch-uncertainty","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"classifier-calibration","task_name":"Classifier calibration"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"out-of-distribution-detection","task_name":"Out-of-Distribution Detection"},{"task_slug":"uncertainty-quantification","task_name":"Uncertainty Quantification"}],"methods":[{"method_slug":"deep-ensembles","method_name":"Deep Ensembles"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.09184","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.09184"}},"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/ENSTA-U2IS-AI/torch-uncertainty","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_fixture":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"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":"5c7038c35796dddf","entry":"packed_linear","repo":"ENSTA-U2IS-AI/torch-uncertainty","repo_kind":"official","path":"src/torch_uncertainty/layers/packed.py","file_url":"https://github.com/ENSTA-U2IS-AI/torch-uncertainty/blob/HEAD/src/torch_uncertainty/layers/packed.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5c7038c35796dddf"}},{"code_sha256_prefix":"1be634ae9abe064e","entry":"PackedLinear","repo":"ENSTA-U2IS-AI/torch-uncertainty","repo_kind":"official","path":"src/torch_uncertainty/layers/packed.py","file_url":"https://github.com/ENSTA-U2IS-AI/torch-uncertainty/blob/HEAD/src/torch_uncertainty/layers/packed.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":"1be634ae9abe064e"}},{"code_sha256_prefix":"05ffce263e88e176","entry":"check_packed_parameters_consistency","repo":"ENSTA-U2IS-AI/torch-uncertainty","repo_kind":"official","path":"src/torch_uncertainty/layers/packed.py","file_url":"https://github.com/ENSTA-U2IS-AI/torch-uncertainty/blob/HEAD/src/torch_uncertainty/layers/packed.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":"05ffce263e88e176"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}