{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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":{"syntology_url":"https://syntology.ai/paper/1705.07832","atlas_url":"https://app.syntology.ai/?focus=1705.07832","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.07832"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1705.07832"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1705.07832"},"call":"get_harvested_code_for_paper(arxiv_id=\"1705.07832\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"1705.07832"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1705.07832\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1705.07832"},"call":"get_concepts_for_paper(arxiv_id=\"1705.07832\")"}],"by_repo":[{"repo":"MSRDL/Deep4Cast","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1609.03499"],"harvested_for_calls":[{"arxiv_id":"1609.03499","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1609.03499"},"call":"get_harvested_code_for_paper(arxiv_id=\"1609.03499\")"}]},{"repo":"aurelio-amerio/concretedropout","kind":"listed","samples":2,"ran":2,"instrument":0,"unverified":0},{"repo":"danielkelshaw/ConcreteDropout","kind":"listed","samples":2,"ran":2,"instrument":0,"unverified":0},{"repo":"giarcieri/assessing-the-influence-of-models-on-the-performance-of-reinforcement-learning-algorithms","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1810.05546"],"harvested_for_calls":[{"arxiv_id":"1810.05546","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1810.05546"},"call":"get_harvested_code_for_paper(arxiv_id=\"1810.05546\")"}]},{"repo":"yaringal/ConcreteDropout","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/1705.07832.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/1705.07832.svg"},"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},"n_samples":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"listed":{"samples":4,"ran":4,"n_ran_checked":4,"n_instrument":0,"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,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":4,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-22","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"339021a7d7ac2660","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,"signature":"N:int/0/int, tau:float/0/float, cross_entropy_loss:bool/0/bool","fixture_out_type":"float","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"339021a7d7ac2660"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"339021a7d7ac2660"}},{"code_sha256":"8e4a3c9d0fea8adc","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,"signature":"N:int/0/int, l:float/0/float, tau:float/0/float","fixture_out_type":"float","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"8e4a3c9d0fea8adc"}},{"code_sha256":"8a04fa1a0775cf9b","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,"signature":"model:callable/0/?, testloader:SimpleDataLoader/0/?, device:str/0/str","fixture_out_type":"tuple","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/test","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"8a04fa1a0775cf9b"}},{"code_sha256":"4b10c277faf961e9","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,"signature":"model:callable/0/?, trainloader:DataLoader/0/?, optimiser:SGD/0/?, epoch:int/0/int, device:str/0/str","fixture_out_type":"float","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/train","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"4b10c277faf961e9"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"afd4676365d8a17ea7c1b2ab12d595c17222ab2f336c2f96b6973ec9270da7da","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}