{"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/mars-masked-automatic-ranks-selection-in","title":"MARS: Masked Automatic Ranks Selection in Tensor Decompositions","arxiv_id":"2006.10859","date":"2020-06-18","proceeding":null,"authors":["Maxim Kodryan","Dmitry Kropotov","Dmitry Vetrov"],"abstract":"Tensor decomposition methods have proven effective in various applications, including compression and acceleration of neural networks. At the same time, the problem of determining optimal decomposition ranks, which present the crucial parameter controlling the compression-accuracy trade-off, is still acute. In this paper, we introduce MARS -- a new efficient method for the automatic selection of ranks in general tensor decompositions. During training, the procedure learns binary masks over decomposition cores that \"select\" the optimal tensor structure. The learning is performed via relaxed maximum a posteriori (MAP) estimation in a specific Bayesian model and can be naturally embedded into the standard neural network training routine. Diverse experiments demonstrate that MARS achieves better results compared to previous works in various tasks.","url_abs":"https://arxiv.org/abs/2006.10859v3","url_pdf":"https://arxiv.org/pdf/2006.10859v3.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":"mars-masked-automatic-ranks-selection-in","repo_url":"https://github.com/maxbourdon/mars","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"tensor-decomposition","task_name":"Tensor Decomposition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.10859","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.10859"}},"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/maxbourdon/mars","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"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":"5dc1bc877c27464d","entry":"compute_cum_reg","repo":"maxbourdon/mars","repo_kind":"official","path":"main/mars.py","file_url":"https://github.com/maxbourdon/mars/blob/HEAD/main/mars.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":"5dc1bc877c27464d"}},{"code_sha256_prefix":"8dd5732a5e8510ec","entry":"get_MARS_attr","repo":"maxbourdon/mars","repo_kind":"official","path":"main/mars.py","file_url":"https://github.com/maxbourdon/mars/blob/HEAD/main/mars.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":"8dd5732a5e8510ec"}},{"code_sha256_prefix":"1ce09009659054ee","entry":"masked_dense_tt_matmul","repo":"maxbourdon/mars","repo_kind":"official","path":"main/tensorized_models.py","file_url":"https://github.com/maxbourdon/mars/blob/HEAD/main/tensorized_models.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":"1ce09009659054ee"}},{"code_sha256_prefix":"9f60be7520b1ad63","entry":"masked_full","repo":"maxbourdon/mars","repo_kind":"official","path":"main/tensorized_models.py","file_url":"https://github.com/maxbourdon/mars/blob/HEAD/main/tensorized_models.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":"9f60be7520b1ad63"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}