{"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/concrete-dropout","title":"Concrete Dropout","arxiv_id":"1705.07832","date":"2017-05-22","proceeding":"NeurIPS 2017 12","authors":["Yarin Gal","Jiri Hron","Alex Kendall"],"abstract":"Dropout is used as a practical tool to obtain uncertainty estimates in large\nvision models and reinforcement learning (RL) tasks. But to obtain\nwell-calibrated uncertainty estimates, a grid-search over the dropout\nprobabilities is necessary - a prohibitive operation with large models, and an\nimpossible one with RL. We propose a new dropout variant which gives improved\nperformance and better calibrated uncertainties. Relying on recent developments\nin Bayesian deep learning, we use a continuous relaxation of dropout's discrete\nmasks. Together with a principled optimisation objective, this allows for\nautomatic tuning of the dropout probability in large models, and as a result\nfaster experimentation cycles. In RL this allows the agent to adapt its\nuncertainty dynamically as more data is observed. We analyse the proposed\nvariant extensively on a range of tasks, and give insights into common practice\nin the field where larger dropout probabilities are often used in deeper model\nlayers.","url_abs":"http://arxiv.org/abs/1705.07832v1","url_pdf":"http://arxiv.org/pdf/1705.07832v1.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":"concrete-dropout","repo_url":"https://github.com/MSRDL/Deep4Cast","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"concrete-dropout","repo_url":"https://github.com/aurelio-amerio/concretedropout","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"concrete-dropout","repo_url":"https://github.com/danielkelshaw/ConcreteDropout","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"concrete-dropout","repo_url":"https://github.com/giarcieri/assessing-the-influence-of-models-on-the-performance-of-reinforcement-learning-algorithms","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"concrete-dropout","repo_url":"https://github.com/yaringal/ConcreteDropout","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[{"method_slug":"concrete-dropout","method_name":"Concrete Dropout"},{"method_slug":"dropout","method_name":"Dropout"}],"datasets_introduced":[],"methods_introduced":[{"slug":"concrete-dropout","name":"Concrete Dropout","full_name":"Concrete Dropout"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.07832","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.07832"}},"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/MSRDL/Deep4Cast","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yaringal/ConcreteDropout","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/danielkelshaw/ConcreteDropout","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/giarcieri/assessing-the-influence-of-models-on-the-performance-of-reinforcement-learning-algorithms","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aurelio-amerio/concretedropout","reach":null}],"summary":{"ran_honours":3,"ran_violates":1},"by_repo_kind":{"listed":{"samples":4,"ran":4,"repositories":2}},"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":"339021a7d7ac2660","entry":"get_dropout_regularizer","repo":"aurelio-amerio/concretedropout","repo_kind":"listed","path":"src/ConcreteDropout/pytorch.py","file_url":"https://github.com/aurelio-amerio/concretedropout/blob/HEAD/src/ConcreteDropout/pytorch.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":"339021a7d7ac2660"}},{"code_sha256_prefix":"8e4a3c9d0fea8adc","entry":"get_weight_regularizer","repo":"aurelio-amerio/concretedropout","repo_kind":"listed","path":"src/ConcreteDropout/pytorch.py","file_url":"https://github.com/aurelio-amerio/concretedropout/blob/HEAD/src/ConcreteDropout/pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8e4a3c9d0fea8adc"}},{"code_sha256_prefix":"8a04fa1a0775cf9b","entry":"test","repo":"danielkelshaw/ConcreteDropout","repo_kind":"listed","path":"mnist_example.py","file_url":"https://github.com/danielkelshaw/ConcreteDropout/blob/HEAD/mnist_example.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8a04fa1a0775cf9b"}},{"code_sha256_prefix":"4b10c277faf961e9","entry":"train","repo":"danielkelshaw/ConcreteDropout","repo_kind":"listed","path":"mnist_example.py","file_url":"https://github.com/danielkelshaw/ConcreteDropout/blob/HEAD/mnist_example.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4b10c277faf961e9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}