{"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/noise-reuse-in-online-evolution-strategies","title":"Variance-Reduced Gradient Estimation via Noise-Reuse in Online Evolution Strategies","arxiv_id":"2304.12180","date":"2023-04-21","proceeding":"NeurIPS 2023 11","authors":["Oscar Li","James Harrison","Jascha Sohl-Dickstein","Virginia Smith","Luke Metz"],"abstract":"Unrolled computation graphs are prevalent throughout machine learning but present challenges to automatic differentiation (AD) gradient estimation methods when their loss functions exhibit extreme local sensitivtiy, discontinuity, or blackbox characteristics. In such scenarios, online evolution strategies methods are a more capable alternative, while being more parallelizable than vanilla evolution strategies (ES) by interleaving partial unrolls and gradient updates. In this work, we propose a general class of unbiased online evolution strategies methods. We analytically and empirically characterize the variance of this class of gradient estimators and identify the one with the least variance, which we term Noise-Reuse Evolution Strategies (NRES). Experimentally, we show NRES results in faster convergence than existing AD and ES methods in terms of wall-clock time and number of unroll steps across a variety of applications, including learning dynamical systems, meta-training learned optimizers, and reinforcement learning.","url_abs":"https://arxiv.org/abs/2304.12180v2","url_pdf":"https://arxiv.org/pdf/2304.12180v2.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":"noise-reuse-in-online-evolution-strategies","repo_url":"https://github.com/oscarcarli/noise-reuse-evolution-strategies","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2304.12180","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.12180"}},"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/OscarcarLi/Noise-Reuse-Evolution-Strategies","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/oscarcarli/noise-reuse-evolution-strategies","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":2,"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":2,"samples":[{"code_sha256_prefix":"bf3cf61f66c2b013","entry":"tree_zip_jnp","repo":"oscarcarli/noise-reuse-evolution-strategies","repo_kind":"official","path":"main_training.py","file_url":"https://github.com/oscarcarli/noise-reuse-evolution-strategies/blob/HEAD/main_training.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bf3cf61f66c2b013"}},{"code_sha256_prefix":"3e4244e3b45ed852","entry":"tree_zip_onp","repo":"oscarcarli/noise-reuse-evolution-strategies","repo_kind":"official","path":"main_training.py","file_url":"https://github.com/oscarcarli/noise-reuse-evolution-strategies/blob/HEAD/main_training.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3e4244e3b45ed852"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}