{"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/mars-meta-learning-as-score-matching-in-the","title":"MARS: Meta-Learning as Score Matching in the Function Space","arxiv_id":"2210.13319","date":"2022-10-24","proceeding":null,"authors":["Krunoslav Lehman Pavasovic","Jonas Rothfuss","Andreas Krause"],"abstract":"Meta-learning aims to extract useful inductive biases from a set of related datasets. In Bayesian meta-learning, this is typically achieved by constructing a prior distribution over neural network parameters. However, specifying families of computationally viable prior distributions over the high-dimensional neural network parameters is difficult. As a result, existing approaches resort to meta-learning restrictive diagonal Gaussian priors, severely limiting their expressiveness and performance. To circumvent these issues, we approach meta-learning through the lens of functional Bayesian neural network inference, which views the prior as a stochastic process and performs inference in the function space. Specifically, we view the meta-training tasks as samples from the data-generating process and formalize meta-learning as empirically estimating the law of this stochastic process. Our approach can seamlessly acquire and represent complex prior knowledge by meta-learning the score function of the data-generating process marginals instead of parameter space priors. In a comprehensive benchmark, we demonstrate that our method achieves state-of-the-art performance in terms of predictive accuracy and substantial improvements in the quality of uncertainty estimates.","url_abs":"https://arxiv.org/abs/2210.13319v3","url_pdf":"https://arxiv.org/pdf/2210.13319v3.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":"mars-meta-learning-as-score-matching-in-the","repo_url":"https://github.com/krunolp/mars","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null}],"tasks":[{"task_slug":"meta-learning","task_name":"Meta-Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.13319","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.13319"}},"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/krunolp/mars","reach":null}],"summary":{"ran_violates":1,"ran_draft_wrong":2,"ran_fixture":1,"unverified":2},"by_repo_kind":{"official":{"samples":2,"ran":1,"repositories":1},"community":{"samples":3,"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":1,"samples":[{"code_sha256_prefix":"6038e0fc3954038b","entry":"exists","repo":"AGI-Arena/MARS","repo_kind":"community","path":"MARS/optimizers/mars.py","file_url":"https://github.com/AGI-Arena/MARS/blob/HEAD/MARS/optimizers/mars.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6038e0fc3954038b"}},{"code_sha256_prefix":"c7059fb2b562bebf","entry":"get_f","repo":"krunolp/mars","repo_kind":"official","path":"MARS/modules/score_network/score_network.py","file_url":"https://github.com/krunolp/mars/blob/HEAD/MARS/modules/score_network/score_network.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c7059fb2b562bebf"}},{"code_sha256_prefix":"92101b06ecbf1f1e","entry":"new_gelu","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"92101b06ecbf1f1e"}},{"code_sha256_prefix":"2de282511e1a7a18","entry":"update_fn","repo":"AGI-Arena/MARS","repo_kind":"community","path":"MARS/optimizers/mars.py","file_url":"https://github.com/AGI-Arena/MARS/blob/HEAD/MARS/optimizers/mars.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2de282511e1a7a18"}},{"code_sha256_prefix":"42b6f8e84b53ac68","entry":"NewtonSchulz","repo":"AGI-Arena/MARS","repo_kind":"community","path":"MARS/optimizers/mars.py","file_url":"https://github.com/AGI-Arena/MARS/blob/HEAD/MARS/optimizers/mars.py","link_basis":"first_harvest_node","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":"42b6f8e84b53ac68"}},{"code_sha256_prefix":"0e4649395693f712","entry":"spectr_norm","repo":"krunolp/mars","repo_kind":"official","path":"MARS/modules/score_network/score_network.py","file_url":"https://github.com/krunolp/mars/blob/HEAD/MARS/modules/score_network/score_network.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":"0e4649395693f712"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}