{"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/the-power-of-log-sum-exp-sequential-density","title":"The Power of Log-Sum-Exp: Sequential Density Ratio Matrix Estimation for Speed-Accuracy Optimization","arxiv_id":"2105.13636","date":"2021-05-28","proceeding":null,"authors":["Taiki Miyagawa","Akinori F. Ebihara"],"abstract":"We propose a model for multiclass classification of time series to make a prediction as early and as accurate as possible. The matrix sequential probability ratio test (MSPRT) is known to be asymptotically optimal for this setting, but contains a critical assumption that hinders broad real-world applications; the MSPRT requires the underlying probability density. To address this problem, we propose to solve density ratio matrix estimation (DRME), a novel type of density ratio estimation that consists of estimating matrices of multiple density ratios with constraints and thus is more challenging than the conventional density ratio estimation. We propose a log-sum-exp-type loss function (LSEL) for solving DRME and prove the following: (i) the LSEL provides the true density ratio matrix as the sample size of the training set increases (consistency); (ii) it assigns larger gradients to harder classes (hard class weighting effect); and (iii) it provides discriminative scores even on class-imbalanced datasets (guess-aversion). Our overall architecture for early classification, MSPRT-TANDEM, statistically significantly outperforms baseline models on four datasets including action recognition, especially in the early stage of sequential observations. Our code and datasets are publicly available at: https://github.com/TaikiMiyagawa/MSPRT-TANDEM.","url_abs":"https://arxiv.org/abs/2105.13636v2","url_pdf":"https://arxiv.org/pdf/2105.13636v2.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":"the-power-of-log-sum-exp-sequential-density","repo_url":"https://github.com/TaikiMiyagawa/MSPRT-TANDEM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"density-ratio-estimation","task_name":"Density Ratio Estimation"},{"task_slug":"early-classification","task_name":"Early  Classification"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2105.13636","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.13636"}},"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/TaikiMiyagawa/MSPRT-TANDEM","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"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":"61d078878105d29d","entry":"get_batch_norm_layer","repo":"TaikiMiyagawa/MSPRT-TANDEM","repo_kind":"official","path":"models/backbones_fe.py","file_url":"https://github.com/TaikiMiyagawa/MSPRT-TANDEM/blob/HEAD/models/backbones_fe.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"61d078878105d29d"}},{"code_sha256_prefix":"93f9562775b33b2c","entry":"get_ressize_dependent_params","repo":"TaikiMiyagawa/MSPRT-TANDEM","repo_kind":"official","path":"models/backbones_fe.py","file_url":"https://github.com/TaikiMiyagawa/MSPRT-TANDEM/blob/HEAD/models/backbones_fe.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"93f9562775b33b2c"}},{"code_sha256_prefix":"c761d6a6ea580871","entry":"np_to_tfr_nosaic_mnist","repo":"TaikiMiyagawa/MSPRT-TANDEM","repo_kind":"official","path":"data-directory/make_nmnist-100f.py","file_url":"https://github.com/TaikiMiyagawa/MSPRT-TANDEM/blob/HEAD/data-directory/make_nmnist-100f.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c761d6a6ea580871"}},{"code_sha256_prefix":"fcda594cb6795f6d","entry":"read_tfrecords_UCF101","repo":"TaikiMiyagawa/MSPRT-TANDEM","repo_kind":"official","path":"datasets/data_processing.py","file_url":"https://github.com/TaikiMiyagawa/MSPRT-TANDEM/blob/HEAD/datasets/data_processing.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fcda594cb6795f6d"}},{"code_sha256_prefix":"4af3235ea62f0a85","entry":"read_tfrecords_nosaic_mnist","repo":"TaikiMiyagawa/MSPRT-TANDEM","repo_kind":"official","path":"datasets/data_processing.py","file_url":"https://github.com/TaikiMiyagawa/MSPRT-TANDEM/blob/HEAD/datasets/data_processing.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4af3235ea62f0a85"}},{"code_sha256_prefix":"37711c4b2ac3a76f","entry":"which_dataset_UCF101","repo":"TaikiMiyagawa/MSPRT-TANDEM","repo_kind":"official","path":"datasets/data_processing.py","file_url":"https://github.com/TaikiMiyagawa/MSPRT-TANDEM/blob/HEAD/datasets/data_processing.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"37711c4b2ac3a76f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}