{"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/adadelta-an-adaptive-learning-rate-method","title":"ADADELTA: An Adaptive Learning Rate Method","arxiv_id":"1212.5701","date":"2012-12-22","proceeding":null,"authors":["Matthew D. Zeiler"],"abstract":"We present a novel per-dimension learning rate method for gradient descent\ncalled ADADELTA. The method dynamically adapts over time using only first order\ninformation and has minimal computational overhead beyond vanilla stochastic\ngradient descent. The method requires no manual tuning of a learning rate and\nappears robust to noisy gradient information, different model architecture\nchoices, various data modalities and selection of hyperparameters. We show\npromising results compared to other methods on the MNIST digit classification\ntask using a single machine and on a large scale voice dataset in a distributed\ncluster environment.","url_abs":"http://arxiv.org/abs/1212.5701v1","url_pdf":"http://arxiv.org/pdf/1212.5701v1.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":"adadelta-an-adaptive-learning-rate-method","repo_url":"https://github.com/Arko98/Gradient-Descent-Algorithms","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"adadelta-an-adaptive-learning-rate-method","repo_url":"https://github.com/arobey1/mbrdl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"adadelta-an-adaptive-learning-rate-method","repo_url":"https://github.com/bratao/PySeqLab","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"adadelta-an-adaptive-learning-rate-method","repo_url":"https://github.com/harshraj11584/Paper-Implementation-Overview-Gradient-Descent-Optimization-Algorithms","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"adadelta-an-adaptive-learning-rate-method","repo_url":"https://github.com/harshraj11584/Paper-Implementation-Overview-Gradient-Descent-Optimization-Sebastian-Ruder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"adadelta-an-adaptive-learning-rate-method","repo_url":"https://github.com/hx123123/optimization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"adadelta-an-adaptive-learning-rate-method","repo_url":"https://github.com/mohamedameen93/German-Traffic-Sign-Classification-Using-TensorFlow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"adadelta-an-adaptive-learning-rate-method","repo_url":"https://github.com/nyatadecocoa/Machine_Learning_Midterm_Assignment_2019","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"adadelta-an-adaptive-learning-rate-method","repo_url":"https://github.com/rahulsonone1234/Traffic-Sign-Recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"adadelta-an-adaptive-learning-rate-method","repo_url":"https://github.com/rahulsonone1234/traffic-sign-","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"adadelta-an-adaptive-learning-rate-method","repo_url":"https://github.com/suzyi/optimization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"adadelta-an-adaptive-learning-rate-method","repo_url":"https://github.com/uzh-dqbm-cmi/PySeqLab","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"}],"methods":[{"method_slug":"adadelta","method_name":"AdaDelta"}],"datasets_introduced":[],"methods_introduced":[{"slug":"adadelta","name":"AdaDelta","full_name":"AdaDelta"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1212.5701","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1212.5701"}},"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/suzyi/optimization","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/harshraj11584/Paper-Implementation-Overview-Gradient-Descent-Optimization-Sebastian-Ruder","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/arobey1/mbrdl","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mohamedameen93/German-Traffic-Sign-Classification-Using-TensorFlow","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/harshraj11584/Paper-Implementation-Overview-Gradient-Descent-Optimization-Algorithms","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rahulsonone1234/Traffic-Sign-Recognition","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nyatadecocoa/Machine_Learning_Midterm_Assignment_2019","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rahulsonone1234/traffic-sign-","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bratao/PySeqLab","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Arko98/Gradient-Descent-Algorithms","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hx123123/optimization","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/uzh-dqbm-cmi/PySeqLab","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"listed":{"samples":6,"ran":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,"samples":[{"code_sha256_prefix":"8ebb55a656ed779b","entry":"create_directory","repo":"bratao/PySeqLab","repo_kind":"listed","path":"pyseqlab/utilities.py","file_url":"https://github.com/bratao/PySeqLab/blob/HEAD/pyseqlab/utilities.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8ebb55a656ed779b"}},{"code_sha256_prefix":"dee768aa793f867c","entry":"cross_entropy","repo":"Arko98/Gradient-Descent-Algorithms","repo_kind":"listed","path":"Algorithms/Adagrad.py","file_url":"https://github.com/Arko98/Gradient-Descent-Algorithms/blob/HEAD/Algorithms/Adagrad.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dee768aa793f867c"}},{"code_sha256_prefix":"6a2fbba8acf6ffbd","entry":"f","repo":"Arko98/Gradient-Descent-Algorithms","repo_kind":"listed","path":"Algorithms/Adagrad.py","file_url":"https://github.com/Arko98/Gradient-Descent-Algorithms/blob/HEAD/Algorithms/Adagrad.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6a2fbba8acf6ffbd"}},{"code_sha256_prefix":"724118fd0939ea91","entry":"generate_partition_boundaries","repo":"bratao/PySeqLab","repo_kind":"listed","path":"pyseqlab/utilities.py","file_url":"https://github.com/bratao/PySeqLab/blob/HEAD/pyseqlab/utilities.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"724118fd0939ea91"}},{"code_sha256_prefix":"a9abce3860e6e7d8","entry":"mse","repo":"Arko98/Gradient-Descent-Algorithms","repo_kind":"listed","path":"Algorithms/Adagrad.py","file_url":"https://github.com/Arko98/Gradient-Descent-Algorithms/blob/HEAD/Algorithms/Adagrad.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a9abce3860e6e7d8"}},{"code_sha256_prefix":"ef2ea0dab0aa3d62","entry":"vectorized_logsumexp","repo":"bratao/PySeqLab","repo_kind":"listed","path":"pyseqlab/utilities.py","file_url":"https://github.com/bratao/PySeqLab/blob/HEAD/pyseqlab/utilities.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ef2ea0dab0aa3d62"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}