{"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/newton-less-sparsification-without-trade-offs","title":"Newton-LESS: Sparsification without Trade-offs for the Sketched Newton Update","arxiv_id":"2107.07480","date":"2021-07-15","proceeding":"NeurIPS 2021 12","authors":["Michał Dereziński","Jonathan Lacotte","Mert Pilanci","Michael W. Mahoney"],"abstract":"In second-order optimization, a potential bottleneck can be computing the Hessian matrix of the optimized function at every iteration. Randomized sketching has emerged as a powerful technique for constructing estimates of the Hessian which can be used to perform approximate Newton steps. This involves multiplication by a random sketching matrix, which introduces a trade-off between the computational cost of sketching and the convergence rate of the optimization algorithm. A theoretically desirable but practically much too expensive choice is to use a dense Gaussian sketching matrix, which produces unbiased estimates of the exact Newton step and which offers strong problem-independent convergence guarantees. We show that the Gaussian sketching matrix can be drastically sparsified, significantly reducing the computational cost of sketching, without substantially affecting its convergence properties. This approach, called Newton-LESS, is based on a recently introduced sketching technique: LEverage Score Sparsified (LESS) embeddings. We prove that Newton-LESS enjoys nearly the same problem-independent local convergence rate as Gaussian embeddings, not just up to constant factors but even down to lower order terms, for a large class of optimization tasks. In particular, this leads to a new state-of-the-art convergence result for an iterative least squares solver. Finally, we extend LESS embeddings to include uniformly sparsified random sign matrices which can be implemented efficiently and which perform well in numerical experiments.","url_abs":"https://arxiv.org/abs/2107.07480v1","url_pdf":"https://arxiv.org/pdf/2107.07480v1.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":"newton-less-sparsification-without-trade-offs","repo_url":"https://github.com/lessketching/newtonsketch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2107.07480","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.07480"}},"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/lessketching/newtonsketch","reach":null}],"summary":{"ran_honours":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":4,"samples":[{"code_sha256_prefix":"44b4ae881a41a617","entry":"hadamard","repo":"lessketching/newtonsketch","repo_kind":"official","path":"sketches.py","file_url":"https://github.com/lessketching/newtonsketch/blob/HEAD/sketches.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"44b4ae881a41a617"}},{"code_sha256_prefix":"0fc4ab859a10707b","entry":"rrs","repo":"lessketching/newtonsketch","repo_kind":"official","path":"sketches.py","file_url":"https://github.com/lessketching/newtonsketch/blob/HEAD/sketches.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0fc4ab859a10707b"}},{"code_sha256_prefix":"fb8d843bdc74ecf8","entry":"direct_method","repo":"lessketching/newtonsketch","repo_kind":"official","path":"solvers.py","file_url":"https://github.com/lessketching/newtonsketch/blob/HEAD/solvers.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":"fb8d843bdc74ecf8"}},{"code_sha256_prefix":"89ed00b1c63f9dfa","entry":"rrs_lev_scores","repo":"lessketching/newtonsketch","repo_kind":"official","path":"sketches.py","file_url":"https://github.com/lessketching/newtonsketch/blob/HEAD/sketches.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":"89ed00b1c63f9dfa"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}