{"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/random-warping-series-a-random-features","title":"Random Warping Series: A Random Features Method for Time-Series Embedding","arxiv_id":"1809.05259","date":"2018-09-14","proceeding":null,"authors":["Lingfei Wu","Ian En-Hsu Yen","Jin-Feng Yi","Fangli Xu","Qi Lei","Michael Witbrock"],"abstract":"Time series data analytics has been a problem of substantial interests for\ndecades, and Dynamic Time Warping (DTW) has been the most widely adopted\ntechnique to measure dissimilarity between time series. A number of\nglobal-alignment kernels have since been proposed in the spirit of DTW to\nextend its use to kernel-based estimation method such as support vector\nmachine. However, those kernels suffer from diagonal dominance of the Gram\nmatrix and a quadratic complexity w.r.t. the sample size. In this work, we\nstudy a family of alignment-aware positive definite (p.d.) kernels, with its\nfeature embedding given by a distribution of \\emph{Random Warping Series\n(RWS)}. The proposed kernel does not suffer from the issue of diagonal\ndominance while naturally enjoys a \\emph{Random Features} (RF) approximation,\nwhich reduces the computational complexity of existing DTW-based techniques\nfrom quadratic to linear in terms of both the number and the length of\ntime-series. We also study the convergence of the RF approximation for the\ndomain of time series of unbounded length. Our extensive experiments on 16\nbenchmark datasets demonstrate that RWS outperforms or matches state-of-the-art\nclassification and clustering methods in both accuracy and computational time.\nOur code and data is available at {\n\\url{https://github.com/IBM/RandomWarpingSeries}}.","url_abs":"http://arxiv.org/abs/1809.05259v1","url_pdf":"http://arxiv.org/pdf/1809.05259v1.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-warping-series-a-random-features","repo_url":"https://github.com/IBM/RandomWarpingSeries","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"dynamic-time-warping","task_name":"Dynamic Time Warping"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"}],"methods":[{"method_slug":"dtw","method_name":"DTW"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.05259","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}