{"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/super-adam-faster-and-universal-framework-of","title":"SUPER-ADAM: Faster and Universal Framework of Adaptive Gradients","arxiv_id":"2106.08208","date":"2021-06-15","proceeding":"NeurIPS 2021 12","authors":["Feihu Huang","Junyi Li","Heng Huang"],"abstract":"Adaptive gradient methods have shown excellent performances for solving many machine learning problems. Although multiple adaptive gradient methods were recently studied, they mainly focus on either empirical or theoretical aspects and also only work for specific problems by using some specific adaptive learning rates. Thus, it is desired to design a universal framework for practical algorithms of adaptive gradients with theoretical guarantee to solve general problems. To fill this gap, we propose a faster and universal framework of adaptive gradients (i.e., SUPER-ADAM) by introducing a universal adaptive matrix that includes most existing adaptive gradient forms. Moreover, our framework can flexibly integrate the momentum and variance reduced techniques. In particular, our novel framework provides the convergence analysis support for adaptive gradient methods under the nonconvex setting. In theoretical analysis, we prove that our SUPER-ADAM algorithm can achieve the best known gradient (i.e., stochastic first-order oracle (SFO)) complexity of $\\tilde{O}(\\epsilon^{-3})$ for finding an $\\epsilon$-stationary point of nonconvex optimization, which matches the lower bound for stochastic smooth nonconvex optimization. In numerical experiments, we employ various deep learning tasks to validate that our algorithm consistently outperforms the existing adaptive algorithms. Code is available at https://github.com/LIJUNYI95/SuperAdam","url_abs":"https://arxiv.org/abs/2106.08208v9","url_pdf":"https://arxiv.org/pdf/2106.08208v9.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":"super-adam-faster-and-universal-framework-of","repo_url":"https://github.com/lijunyi95/superadam","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.08208","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08208"}},"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/LIJUNYI95/SuperAdam","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lijunyi95/superadam","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":4,"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":"cf1cff04ac96cd7d","entry":"SuperAdam","repo":"lijunyi95/superadam","repo_kind":"official","path":"SuperAdam.py","file_url":"https://github.com/lijunyi95/superadam/blob/HEAD/SuperAdam.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cf1cff04ac96cd7d"}},{"code_sha256_prefix":"8d7ec010c29e813b","entry":"format_time","repo":"LIJUNYI95/SuperAdam","repo_kind":"official","path":"utils.py","file_url":"https://github.com/LIJUNYI95/SuperAdam/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8d7ec010c29e813b"}},{"code_sha256_prefix":"7bd3a77007a65eec","entry":"get_mean_and_std","repo":"LIJUNYI95/SuperAdam","repo_kind":"official","path":"utils.py","file_url":"https://github.com/LIJUNYI95/SuperAdam/blob/HEAD/utils.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":"7bd3a77007a65eec"}},{"code_sha256_prefix":"750c06d20dcd9da0","entry":"superadam","repo":"lijunyi95/superadam","repo_kind":"official","path":"SuperAdam.py","file_url":"https://github.com/lijunyi95/superadam/blob/HEAD/SuperAdam.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":"750c06d20dcd9da0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}