{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/random-matrices-in-service-of-ml-footprint","title":"Random matrices in service of ML footprint: ternary random features with no performance loss","arxiv_id":"2110.01899","date":"2021-10-05","proceeding":"ICLR 2022 4","authors":["Hafiz Tiomoko Ali","Zhenyu Liao","Romain Couillet"],"abstract":"In this article, we investigate the spectral behavior of random features kernel matrices of the type ${\\bf K} = \\mathbb{E}_{{\\bf w}} \\left[\\sigma\\left({\\bf w}^{\\sf T}{\\bf x}_i\\right)\\sigma\\left({\\bf w}^{\\sf T}{\\bf x}_j\\right)\\right]_{i,j=1}^n$, with nonlinear function $\\sigma(\\cdot)$, data ${\\bf x}_1, \\ldots, {\\bf x}_n \\in \\mathbb{R}^p$, and random projection vector ${\\bf w} \\in \\mathbb{R}^p$ having i.i.d. entries. In a high-dimensional setting where the number of data $n$ and their dimension $p$ are both large and comparable, we show, under a Gaussian mixture model for the data, that the eigenspectrum of ${\\bf K}$ is independent of the distribution of the i.i.d.(zero-mean and unit-variance) entries of ${\\bf w}$, and only depends on $\\sigma(\\cdot)$ via its (generalized) Gaussian moments $\\mathbb{E}_{z\\sim \\mathcal N(0,1)}[\\sigma'(z)]$ and $\\mathbb{E}_{z\\sim \\mathcal N(0,1)}[\\sigma''(z)]$. As a result, for any kernel matrix ${\\bf K}$ of the form above, we propose a novel random features technique, called Ternary Random Feature (TRF), that (i) asymptotically yields the same limiting kernel as the original ${\\bf K}$ in a spectral sense and (ii) can be computed and stored much more efficiently, by wisely tuning (in a data-dependent manner) the function $\\sigma$ and the random vector ${\\bf w}$, both taking values in $\\{-1,0,1\\}$. The computation of the proposed random features requires no multiplication, and a factor of $b$ times less bits for storage compared to classical random features such as random Fourier features, with $b$ the number of bits to store full precision values. Besides, it appears in our experiments on real data that the substantial gains in computation and storage are accompanied with somewhat improved performances compared to state-of-the-art random features compression/quantization methods.","url_abs":"https://arxiv.org/abs/2110.01899v2","url_pdf":"https://arxiv.org/pdf/2110.01899v2.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":"random-matrices-in-service-of-ml-footprint","repo_url":"https://github.com/hafiztiomoko/ternaryrandomfeatures","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"random-matrices-in-service-of-ml-footprint","repo_url":"https://github.com/model-compression/lossless_compression","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"quantization","task_name":"Quantization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2110.01899","atlas_url":"https://app.syntology.ai/?focus=2110.01899","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2110.01899"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2110.01899\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2110.01899"},"call":"get_concepts_for_paper(arxiv_id=\"2110.01899\")"}],"by_repo":[{"repo":"hafiztiomoko/ternaryrandomfeatures","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"model-compression/lossless_compression","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2403.00258"],"harvested_for_calls":[{"arxiv_id":"2403.00258","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2403.00258"},"call":"get_harvested_code_for_paper(arxiv_id=\"2403.00258\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"48be794d55f1492da3daa18e79abe52b55dcfb3a24c3f4d23d9c7feefaf8c2fe","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}