{"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/addressing-parameter-choice-issues-in","title":"Addressing Parameter Choice Issues in Unsupervised Domain Adaptation by Aggregation","arxiv_id":"2305.01281","date":"2023-05-02","proceeding":null,"authors":["Marius-Constantin Dinu","Markus Holzleitner","Maximilian Beck","Hoan Duc Nguyen","Andrea Huber","Hamid Eghbal-zadeh","Bernhard A. Moser","Sergei Pereverzyev","Sepp Hochreiter","Werner Zellinger"],"abstract":"We study the problem of choosing algorithm hyper-parameters in unsupervised domain adaptation, i.e., with labeled data in a source domain and unlabeled data in a target domain, drawn from a different input distribution. We follow the strategy to compute several models using different hyper-parameters, and, to subsequently compute a linear aggregation of the models. While several heuristics exist that follow this strategy, methods are still missing that rely on thorough theories for bounding the target error. In this turn, we propose a method that extends weighted least squares to vector-valued functions, e.g., deep neural networks. We show that the target error of the proposed algorithm is asymptotically not worse than twice the error of the unknown optimal aggregation. We also perform a large scale empirical comparative study on several datasets, including text, images, electroencephalogram, body sensor signals and signals from mobile phones. Our method outperforms deep embedded validation (DEV) and importance weighted validation (IWV) on all datasets, setting a new state-of-the-art performance for solving parameter choice issues in unsupervised domain adaptation with theoretical error guarantees. We further study several competitive heuristics, all outperforming IWV and DEV on at least five datasets. However, our method outperforms each heuristic on at least five of seven datasets.","url_abs":"https://arxiv.org/abs/2305.01281v1","url_pdf":"https://arxiv.org/pdf/2305.01281v1.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":"addressing-parameter-choice-issues-in","repo_url":"https://github.com/xpitfire/iwa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.01281","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.01281"}},"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/xpitfire/iwa","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"ran_draft_wrong":1,"unverified":10},"by_repo_kind":{"official":{"samples":12,"ran":2,"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":"0cb7cfb326eed8be","entry":"EntropyLoss","repo":"xpitfire/iwa","repo_kind":"official","path":"misc/loss.py","file_url":"https://github.com/xpitfire/iwa/blob/HEAD/misc/loss.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0cb7cfb326eed8be"}},{"code_sha256_prefix":"f4a8968b88a150d1","entry":"guassian_kernel","repo":"xpitfire/iwa","repo_kind":"official","path":"misc/loss.py","file_url":"https://github.com/xpitfire/iwa/blob/HEAD/misc/loss.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f4a8968b88a150d1"}},{"code_sha256_prefix":"1f70402f7b8a5e2a","entry":"MMD","repo":"xpitfire/iwa","repo_kind":"official","path":"misc/loss.py","file_url":"https://github.com/xpitfire/iwa/blob/HEAD/misc/loss.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":"1f70402f7b8a5e2a"}},{"code_sha256_prefix":"0c81f8155dbaa303","entry":"gaussian_kernel_torch","repo":"xpitfire/iwa","repo_kind":"official","path":"misc/aux_da_losses.py","file_url":"https://github.com/xpitfire/iwa/blob/HEAD/misc/aux_da_losses.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":"0c81f8155dbaa303"}},{"code_sha256_prefix":"b0bc80b1655a6802","entry":"get_algorithm_class","repo":"xpitfire/iwa","repo_kind":"official","path":"algorithms/algorithms.py","file_url":"https://github.com/xpitfire/iwa/blob/HEAD/algorithms/algorithms.py","link_basis":"plan_row","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":"b0bc80b1655a6802"}},{"code_sha256_prefix":"f8ac075efb28ded9","entry":"get_backbone_class","repo":"xpitfire/iwa","repo_kind":"official","path":"models/models.py","file_url":"https://github.com/xpitfire/iwa/blob/HEAD/models/models.py","link_basis":"plan_row","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":"f8ac075efb28ded9"}},{"code_sha256_prefix":"8dadd34c7426858e","entry":"get_dataset_class","repo":"xpitfire/iwa","repo_kind":"official","path":"configs/data_model_configs.py","file_url":"https://github.com/xpitfire/iwa/blob/HEAD/configs/data_model_configs.py","link_basis":"plan_row","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":"8dadd34c7426858e"}},{"code_sha256_prefix":"2e9eda214371da15","entry":"norm","repo":"xpitfire/iwa","repo_kind":"official","path":"misc/aux_da_losses.py","file_url":"https://github.com/xpitfire/iwa/blob/HEAD/misc/aux_da_losses.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":"2e9eda214371da15"}},{"code_sha256_prefix":"fd11328b6d9f8a37","entry":"pairwise_distance_torch","repo":"xpitfire/iwa","repo_kind":"official","path":"misc/aux_da_losses.py","file_url":"https://github.com/xpitfire/iwa/blob/HEAD/misc/aux_da_losses.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":"fd11328b6d9f8a37"}},{"code_sha256_prefix":"4fa007fe525637b0","entry":"register_alexnet_features_extraction","repo":"xpitfire/iwa","repo_kind":"official","path":"models/backbone.py","file_url":"https://github.com/xpitfire/iwa/blob/HEAD/models/backbone.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":"4fa007fe525637b0"}},{"code_sha256_prefix":"ee32961979c55ad6","entry":"register_domain_adaptation_features_extraction","repo":"xpitfire/iwa","repo_kind":"official","path":"models/backbone.py","file_url":"https://github.com/xpitfire/iwa/blob/HEAD/models/backbone.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":"ee32961979c55ad6"}},{"code_sha256_prefix":"87715dc23ceed107","entry":"register_resnet_features_extraction","repo":"xpitfire/iwa","repo_kind":"official","path":"models/backbone.py","file_url":"https://github.com/xpitfire/iwa/blob/HEAD/models/backbone.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":"87715dc23ceed107"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}