{"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/trace-norm-regularization-and-faster","title":"Trace norm regularization and faster inference for embedded speech recognition RNNs","arxiv_id":"1710.09026","date":"2017-10-25","proceeding":"ICLR 2018 1","authors":["Markus Kliegl","Siddharth Goyal","Kexin Zhao","Kavya Srinet","Mohammad Shoeybi"],"abstract":"We propose and evaluate new techniques for compressing and speeding up dense\nmatrix multiplications as found in the fully connected and recurrent layers of\nneural networks for embedded large vocabulary continuous speech recognition\n(LVCSR). For compression, we introduce and study a trace norm regularization\ntechnique for training low rank factored versions of matrix multiplications.\nCompared to standard low rank training, we show that our method leads to good\naccuracy versus number of parameter trade-offs and can be used to speed up\ntraining of large models. For speedup, we enable faster inference on ARM\nprocessors through new open sourced kernels optimized for small batch sizes,\nresulting in 3x to 7x speed ups over the widely used gemmlowp library. Beyond\nLVCSR, we expect our techniques and kernels to be more generally applicable to\nembedded neural networks with large fully connected or recurrent layers.","url_abs":"http://arxiv.org/abs/1710.09026v2","url_pdf":"http://arxiv.org/pdf/1710.09026v2.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":"trace-norm-regularization-and-faster","repo_url":"https://github.com/kexinzhao/farm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"kexinzhao/farm","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"a10103581db93a21c3991ee88453b3ed731149221b96b3a7d9b33ada23c54864","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}