{"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/low-precision-random-fourier-features-for","title":"Low-Precision Random Fourier Features for Memory-Constrained Kernel Approximation","arxiv_id":"1811.00155","date":"2018-10-31","proceeding":null,"authors":["Jian Zhang","Avner May","Tri Dao","Christopher Ré"],"abstract":"We investigate how to train kernel approximation methods that generalize well\nunder a memory budget. Building on recent theoretical work, we define a measure\nof kernel approximation error which we find to be more predictive of the\nempirical generalization performance of kernel approximation methods than\nconventional metrics. An important consequence of this definition is that a\nkernel approximation matrix must be high rank to attain close approximation.\nBecause storing a high-rank approximation is memory intensive, we propose using\na low-precision quantization of random Fourier features (LP-RFFs) to build a\nhigh-rank approximation under a memory budget. Theoretically, we show\nquantization has a negligible effect on generalization performance in important\nsettings. Empirically, we demonstrate across four benchmark datasets that\nLP-RFFs can match the performance of full-precision RFFs and the Nystr\\\"{o}m\nmethod, with 3x-10x and 50x-460x less memory, respectively.","url_abs":"http://arxiv.org/abs/1811.00155v2","url_pdf":"http://arxiv.org/pdf/1811.00155v2.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":"low-precision-random-fourier-features-for","repo_url":"https://github.com/HazyResearch/lp_rffs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"quantization","task_name":"Quantization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.00155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.00155"}},"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/HazyResearch/lp_rffs","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"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":0,"samples":[{"code_sha256_prefix":"b6abb22ec16e102d","entry":"delta_approximation","repo":"HazyResearch/lp_rffs","repo_kind":"official","path":"utils/misc_utils.py","file_url":"https://github.com/HazyResearch/lp_rffs/blob/HEAD/utils/misc_utils.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":"b6abb22ec16e102d"}},{"code_sha256_prefix":"f8e06ebdb8086560","entry":"expected_loss","repo":"HazyResearch/lp_rffs","repo_kind":"official","path":"utils/misc_utils.py","file_url":"https://github.com/HazyResearch/lp_rffs/blob/HEAD/utils/misc_utils.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":"f8e06ebdb8086560"}},{"code_sha256_prefix":"7e140b536228260d","entry":"load_data","repo":"HazyResearch/lp_rffs","repo_kind":"official","path":"utils/data_loader.py","file_url":"https://github.com/HazyResearch/lp_rffs/blob/HEAD/utils/data_loader.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":"7e140b536228260d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}