{"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/prospective-learning-learning-for-a-dynamic","title":"Prospective Learning: Learning for a Dynamic Future","arxiv_id":"2411.00109","date":"2024-10-31","proceeding":null,"authors":["Ashwin De Silva","Rahul Ramesh","Rubing Yang","Siyu Yu","Joshua T Vogelstein","Pratik Chaudhari"],"abstract":"In real-world applications, the distribution of the data, and our goals, evolve over time. The prevailing theoretical framework for studying machine learning, namely probably approximately correct (PAC) learning, largely ignores time. As a consequence, existing strategies to address the dynamic nature of data and goals exhibit poor real-world performance. This paper develops a theoretical framework called \"Prospective Learning\" that is tailored for situations when the optimal hypothesis changes over time. In PAC learning, empirical risk minimization (ERM) is known to be consistent. We develop a learner called Prospective ERM, which returns a sequence of predictors that make predictions on future data. We prove that the risk of prospective ERM converges to the Bayes risk under certain assumptions on the stochastic process generating the data. Prospective ERM, roughly speaking, incorporates time as an input in addition to the data. We show that standard ERM as done in PAC learning, without incorporating time, can result in failure to learn when distributions are dynamic. Numerical experiments illustrate that prospective ERM can learn synthetic and visual recognition problems constructed from MNIST and CIFAR-10. Code at https://github.com/neurodata/prolearn.","url_abs":"https://arxiv.org/abs/2411.00109v2","url_pdf":"https://arxiv.org/pdf/2411.00109v2.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":"prospective-learning-learning-for-a-dynamic","repo_url":"https://github.com/neurodata/prolearn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"pac-learning","task_name":"PAC learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.00109","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00109"}},"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":"deterministic:regex_extraction","url":"https://github.com/neurodata/prolearn","reach":{"status":"ok"}}],"summary":{"unverified":11},"by_repo_kind":{"official":{"samples":11,"ran":0,"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":11,"samples":[{"code_sha256_prefix":"ae789d85c04d7e57","entry":"cache_dataload","repo":"neurodata/prolearn","repo_kind":"official","path":"deep_nets/02_train.py","file_url":"https://github.com/neurodata/prolearn/blob/HEAD/deep_nets/02_train.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ae789d85c04d7e57"}},{"code_sha256_prefix":"fef4f2a3cf9bd792","entry":"compare_with_tolerance","repo":"neurodata/prolearn","repo_kind":"official","path":"binary/scenario2.py","file_url":"https://github.com/neurodata/prolearn/blob/HEAD/binary/scenario2.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fef4f2a3cf9bd792"}},{"code_sha256_prefix":"cab81a9c56a9d4b1","entry":"compute_mle","repo":"neurodata/prolearn","repo_kind":"official","path":"binary/scenario1.py","file_url":"https://github.com/neurodata/prolearn/blob/HEAD/binary/scenario1.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cab81a9c56a9d4b1"}},{"code_sha256_prefix":"c94c727c3f5f8dba","entry":"erm_mdp","repo":"neurodata/prolearn","repo_kind":"official","path":"binary/scenario4.py","file_url":"https://github.com/neurodata/prolearn/blob/HEAD/binary/scenario4.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c94c727c3f5f8dba"}},{"code_sha256_prefix":"b2bf1b91cda48011","entry":"get_data","repo":"neurodata/prolearn","repo_kind":"official","path":"binary/scenario4.py","file_url":"https://github.com/neurodata/prolearn/blob/HEAD/binary/scenario4.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b2bf1b91cda48011"}},{"code_sha256_prefix":"0a850dd0c6c555ba","entry":"hypothesis","repo":"neurodata/prolearn","repo_kind":"official","path":"binary/scenario1.py","file_url":"https://github.com/neurodata/prolearn/blob/HEAD/binary/scenario1.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0a850dd0c6c555ba"}},{"code_sha256_prefix":"2e00bf7b786c22a9","entry":"hypothesis","repo":"neurodata/prolearn","repo_kind":"official","path":"binary/scenario1_pMAP.py","file_url":"https://github.com/neurodata/prolearn/blob/HEAD/binary/scenario1_pMAP.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2e00bf7b786c22a9"}},{"code_sha256_prefix":"451d871e12f9861a","entry":"hypothesis","repo":"neurodata/prolearn","repo_kind":"official","path":"binary/scenario2.py","file_url":"https://github.com/neurodata/prolearn/blob/HEAD/binary/scenario2.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"451d871e12f9861a"}},{"code_sha256_prefix":"43324a09de80b5fd","entry":"hypothesis_promap","repo":"neurodata/prolearn","repo_kind":"official","path":"binary/scenario1_pMAP.py","file_url":"https://github.com/neurodata/prolearn/blob/HEAD/binary/scenario1_pMAP.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"43324a09de80b5fd"}},{"code_sha256_prefix":"a69ec6ed4b5fcbbd","entry":"loss","repo":"neurodata/prolearn","repo_kind":"official","path":"binary/scenario1.py","file_url":"https://github.com/neurodata/prolearn/blob/HEAD/binary/scenario1.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a69ec6ed4b5fcbbd"}},{"code_sha256_prefix":"0424fce8d092dd98","entry":"prospective_mdp","repo":"neurodata/prolearn","repo_kind":"official","path":"binary/scenario4.py","file_url":"https://github.com/neurodata/prolearn/blob/HEAD/binary/scenario4.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0424fce8d092dd98"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}