{"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/layer-adaptive-state-pruning-for-deep-state","title":"Layer-Adaptive State Pruning for Deep State Space Models","arxiv_id":"2411.02824","date":"2024-11-05","proceeding":null,"authors":["Minseon Gwak","Seongrok Moon","Joohwan Ko","PooGyeon Park"],"abstract":"Due to the lack of state dimension optimization methods, deep state space models (SSMs) have sacrificed model capacity, training search space, or stability to alleviate computational costs caused by high state dimensions. In this work, we provide a structured pruning method for SSMs, Layer-Adaptive STate pruning (LAST), which reduces the state dimension of each layer in minimizing model-level output energy loss by extending modal truncation for a single system. LAST scores are evaluated using the $\\mathcal{H}_{\\infty}$ norms of subsystems and layer-wise energy normalization. The scores serve as global pruning criteria, enabling cross-layer comparison of states and layer-adaptive pruning. Across various sequence benchmarks, LAST optimizes previous SSMs, revealing the redundancy and compressibility of their state spaces. Notably, we demonstrate that, on average, pruning 33% of states still maintains performance with 0.52% accuracy loss in multi-input multi-output SSMs without retraining. Code is available at https://github.com/msgwak/LAST.","url_abs":"https://arxiv.org/abs/2411.02824v3","url_pdf":"https://arxiv.org/pdf/2411.02824v3.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":"layer-adaptive-state-pruning-for-deep-state","repo_url":"https://github.com/msgwak/last","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok"}}],"tasks":[{"task_slug":"state-space-models","task_name":"State Space Models"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.02824","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.02824"}},"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":"deterministic:regex_extraction","url":"https://github.com/msgwak/LAST","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/msgwak/last","reach":{"status":"ok"}}],"summary":{"ran_fixture":1,"ran":3,"unverified":14},"by_repo_kind":{"official":{"samples":18,"ran":4,"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":18,"samples":[{"code_sha256_prefix":"b4fc72406d2ff673","entry":"binary_operator","repo":"msgwak/last","repo_kind":"official","path":"s5/ssm.py","file_url":"https://github.com/msgwak/last/blob/HEAD/s5/ssm.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b4fc72406d2ff673"}},{"code_sha256_prefix":"ce310b19a858070f","entry":"dequantize","repo":"msgwak/LAST","repo_kind":"official","path":"s5/dataloaders/audio.py","file_url":"https://github.com/msgwak/LAST/blob/HEAD/s5/dataloaders/audio.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ce310b19a858070f"}},{"code_sha256_prefix":"1b76e4737067023f","entry":"minmax_scale","repo":"msgwak/LAST","repo_kind":"official","path":"s5/dataloaders/audio.py","file_url":"https://github.com/msgwak/LAST/blob/HEAD/s5/dataloaders/audio.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1b76e4737067023f"}},{"code_sha256_prefix":"1631cd936e9b1a90","entry":"quantize","repo":"msgwak/LAST","repo_kind":"official","path":"s5/dataloaders/audio.py","file_url":"https://github.com/msgwak/LAST/blob/HEAD/s5/dataloaders/audio.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1631cd936e9b1a90"}},{"code_sha256_prefix":"faeebb869aee2124","entry":"cosine_annealing","repo":"msgwak/LAST","repo_kind":"official","path":"s5/train_helpers.py","file_url":"https://github.com/msgwak/LAST/blob/HEAD/s5/train_helpers.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"faeebb869aee2124"}},{"code_sha256_prefix":"476b5f7f116d7c9b","entry":"create_lra_imdb_classification_dataset","repo":"msgwak/LAST","repo_kind":"official","path":"s5/dataloading.py","file_url":"https://github.com/msgwak/LAST/blob/HEAD/s5/dataloading.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"476b5f7f116d7c9b"}},{"code_sha256_prefix":"52bd0069ea925687","entry":"create_lra_listops_classification_dataset","repo":"msgwak/LAST","repo_kind":"official","path":"s5/dataloading.py","file_url":"https://github.com/msgwak/LAST/blob/HEAD/s5/dataloading.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"52bd0069ea925687"}},{"code_sha256_prefix":"25edc240223b76c0","entry":"deprecated","repo":"msgwak/LAST","repo_kind":"official","path":"s5/dataloaders/base.py","file_url":"https://github.com/msgwak/LAST/blob/HEAD/s5/dataloaders/base.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"25edc240223b76c0"}},{"code_sha256_prefix":"c0135e087b049ad1","entry":"discretize_bilinear","repo":"msgwak/last","repo_kind":"official","path":"s5/ssm.py","file_url":"https://github.com/msgwak/last/blob/HEAD/s5/ssm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c0135e087b049ad1"}},{"code_sha256_prefix":"f9485e8e0d1e9aee","entry":"discretize_zoh","repo":"msgwak/last","repo_kind":"official","path":"s5/ssm.py","file_url":"https://github.com/msgwak/last/blob/HEAD/s5/ssm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f9485e8e0d1e9aee"}},{"code_sha256_prefix":"a2cd676d4d4c4910","entry":"linear_warmup","repo":"msgwak/LAST","repo_kind":"official","path":"s5/train_helpers.py","file_url":"https://github.com/msgwak/LAST/blob/HEAD/s5/train_helpers.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a2cd676d4d4c4910"}},{"code_sha256_prefix":"72d464924b5dee96","entry":"listops_tokenizer","repo":"msgwak/LAST","repo_kind":"official","path":"s5/dataloaders/lra.py","file_url":"https://github.com/msgwak/LAST/blob/HEAD/s5/dataloaders/lra.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"72d464924b5dee96"}},{"code_sha256_prefix":"2b5694fa1220f8bd","entry":"make_DPLR_HiPPO","repo":"msgwak/LAST","repo_kind":"official","path":"s5/ssm_init.py","file_url":"https://github.com/msgwak/LAST/blob/HEAD/s5/ssm_init.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2b5694fa1220f8bd"}},{"code_sha256_prefix":"3f26e3f7ea0487f3","entry":"make_HiPPO","repo":"msgwak/LAST","repo_kind":"official","path":"s5/ssm_init.py","file_url":"https://github.com/msgwak/LAST/blob/HEAD/s5/ssm_init.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3f26e3f7ea0487f3"}},{"code_sha256_prefix":"0b867bda221aedfc","entry":"make_NPLR_HiPPO","repo":"msgwak/LAST","repo_kind":"official","path":"s5/ssm_init.py","file_url":"https://github.com/msgwak/LAST/blob/HEAD/s5/ssm_init.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0b867bda221aedfc"}},{"code_sha256_prefix":"508a42e36707cd15","entry":"make_data_loader","repo":"msgwak/LAST","repo_kind":"official","path":"s5/dataloading.py","file_url":"https://github.com/msgwak/LAST/blob/HEAD/s5/dataloading.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"508a42e36707cd15"}},{"code_sha256_prefix":"261d3ddc455af2a0","entry":"masked_meanpool","repo":"msgwak/LAST","repo_kind":"official","path":"s5/seq_model.py","file_url":"https://github.com/msgwak/LAST/blob/HEAD/s5/seq_model.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"261d3ddc455af2a0"}},{"code_sha256_prefix":"2802de0d2519b69a","entry":"reduce_lr_on_plateau","repo":"msgwak/LAST","repo_kind":"official","path":"s5/train_helpers.py","file_url":"https://github.com/msgwak/LAST/blob/HEAD/s5/train_helpers.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2802de0d2519b69a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}