{"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/empirical-study-on-optimizer-selection-for","title":"Empirical Study on Optimizer Selection for Out-of-Distribution Generalization","arxiv_id":"2211.08583","date":"2022-11-15","proceeding":null,"authors":["Hiroki Naganuma","Kartik Ahuja","Shiro Takagi","Tetsuya Motokawa","Rio Yokota","Kohta Ishikawa","Ikuro Sato","Ioannis Mitliagkas"],"abstract":"Modern deep learning systems do not generalize well when the test data distribution is slightly different to the training data distribution. While much promising work has been accomplished to address this fragility, a systematic study of the role of optimizers and their out-of-distribution generalization performance has not been undertaken. In this study, we examine the performance of popular first-order optimizers for different classes of distributional shift under empirical risk minimization and invariant risk minimization. We address this question for image and text classification using DomainBed, WILDS, and Backgrounds Challenge as testbeds for studying different types of shifts -- namely correlation and diversity shift. We search over a wide range of hyperparameters and examine classification accuracy (in-distribution and out-of-distribution) for over 20,000 models. We arrive at the following findings, which we expect to be helpful for practitioners: i) adaptive optimizers (e.g., Adam) perform worse than non-adaptive optimizers (e.g., SGD, momentum SGD) on out-of-distribution performance. In particular, even though there is no significant difference in in-distribution performance, we show a measurable difference in out-of-distribution performance. ii) in-distribution performance and out-of-distribution performance exhibit three types of behavior depending on the dataset -- linear returns, increasing returns, and diminishing returns. For example, in the training of natural language data using Adam, fine-tuning the performance of in-distribution performance does not significantly contribute to the out-of-distribution generalization performance.","url_abs":"https://arxiv.org/abs/2211.08583v3","url_pdf":"https://arxiv.org/pdf/2211.08583v3.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":"empirical-study-on-optimizer-selection-for","repo_url":"https://github.com/hiroki11x/optimizer_comparison_ood","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"out-of-distribution-generalization","task_name":"Out-of-Distribution Generalization"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"sgd","method_name":"SGD"},{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2211.08583","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.08583"}},"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/hiroki11x/optimizer_comparison_ood","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":4,"ran":1,"unverified":6},"by_repo_kind":{"official":{"samples":11,"ran":5,"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":"ce7990d7ad5821ff","entry":"Classifier","repo":"hiroki11x/optimizer_comparison_ood","repo_kind":"official","path":"domainbed/networks.py","file_url":"https://github.com/hiroki11x/optimizer_comparison_ood/blob/HEAD/domainbed/networks.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ce7990d7ad5821ff"}},{"code_sha256_prefix":"d9def42110729a85","entry":"conv1x1","repo":"hiroki11x/optimizer_comparison_ood","repo_kind":"official","path":"backgrounds_challenge/imagenet_models/leaky_resnet.py","file_url":"https://github.com/hiroki11x/optimizer_comparison_ood/blob/HEAD/backgrounds_challenge/imagenet_models/leaky_resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d9def42110729a85"}},{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":"hiroki11x/optimizer_comparison_ood","repo_kind":"official","path":"backgrounds_challenge/imagenet_models/leaky_resnet.py","file_url":"https://github.com/hiroki11x/optimizer_comparison_ood/blob/HEAD/backgrounds_challenge/imagenet_models/leaky_resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"53fac8d8d949e72b","entry":"get_test_records","repo":"hiroki11x/optimizer_comparison_ood","repo_kind":"official","path":"domainbed/model_selection.py","file_url":"https://github.com/hiroki11x/optimizer_comparison_ood/blob/HEAD/domainbed/model_selection.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"53fac8d8d949e72b"}},{"code_sha256_prefix":"196cab71d7129d62","entry":"remove_batch_norm_from_resnet","repo":"hiroki11x/optimizer_comparison_ood","repo_kind":"official","path":"domainbed/networks.py","file_url":"https://github.com/hiroki11x/optimizer_comparison_ood/blob/HEAD/domainbed/networks.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"196cab71d7129d62"}},{"code_sha256_prefix":"b0bc80b1655a6802","entry":"get_algorithm_class","repo":"hiroki11x/optimizer_comparison_ood","repo_kind":"official","path":"domainbed/algorithms.py","file_url":"https://github.com/hiroki11x/optimizer_comparison_ood/blob/HEAD/domainbed/algorithms.py","link_basis":"plan_row","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":"b0bc80b1655a6802"}},{"code_sha256_prefix":"d5b851531e5607ed","entry":"leaky_resnet18","repo":"hiroki11x/optimizer_comparison_ood","repo_kind":"official","path":"backgrounds_challenge/imagenet_models/leaky_resnet.py","file_url":"https://github.com/hiroki11x/optimizer_comparison_ood/blob/HEAD/backgrounds_challenge/imagenet_models/leaky_resnet.py","link_basis":"harvester_set","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":"d5b851531e5607ed"}},{"code_sha256_prefix":"7655baef76214ea3","entry":"load_configs","repo":"hiroki11x/optimizer_comparison_ood","repo_kind":"official","path":"backgrounds_challenge/challenge_eval_with_wandb.py","file_url":"https://github.com/hiroki11x/optimizer_comparison_ood/blob/HEAD/backgrounds_challenge/challenge_eval_with_wandb.py","link_basis":"harvester_set","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":"7655baef76214ea3"}},{"code_sha256_prefix":"4663dbc405f4ebb7","entry":"make_layers","repo":"hiroki11x/optimizer_comparison_ood","repo_kind":"official","path":"backgrounds_challenge/imagenet_models/vgg.py","file_url":"https://github.com/hiroki11x/optimizer_comparison_ood/blob/HEAD/backgrounds_challenge/imagenet_models/vgg.py","link_basis":"harvester_set","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":"4663dbc405f4ebb7"}},{"code_sha256_prefix":"e80f6253f6063a60","entry":"resnet18","repo":"hiroki11x/optimizer_comparison_ood","repo_kind":"official","path":"backgrounds_challenge/imagenet_models/resnet.py","file_url":"https://github.com/hiroki11x/optimizer_comparison_ood/blob/HEAD/backgrounds_challenge/imagenet_models/resnet.py","link_basis":"harvester_set","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":"e80f6253f6063a60"}},{"code_sha256_prefix":"129dbbdab666ace4","entry":"resnet18","repo":"hiroki11x/optimizer_comparison_ood","repo_kind":"official","path":"backgrounds_challenge/imagenet_models/wide_resnet.py","file_url":"https://github.com/hiroki11x/optimizer_comparison_ood/blob/HEAD/backgrounds_challenge/imagenet_models/wide_resnet.py","link_basis":"harvester_set","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":"129dbbdab666ace4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}