{"id":"https://openalex.org/W7125945456","doi":"https://doi.org/10.48550/arxiv.2601.19794","title":"Component-Aware Pruning Framework for Neural Network Controllers via Gradient-Based Importance Estimation","display_name":"Component-Aware Pruning Framework for Neural Network Controllers via Gradient-Based Importance Estimation","publication_year":2026,"publication_date":"2026-01-27","ids":{"openalex":"https://openalex.org/W7125945456","doi":"https://doi.org/10.48550/arxiv.2601.19794"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2601.19794","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.19794","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2601.19794","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124100288","display_name":"Ganesh Sundaram","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sundaram, Ganesh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014146001","display_name":"Jonas Ulmen","orcid":"https://orcid.org/0000-0003-1597-1523"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ulmen, Jonas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5003608585","display_name":"Daniel G\u00f6rges","orcid":"https://orcid.org/0000-0001-5504-0972"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"G\u00f6rges, Daniel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.5934000015258789,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.5934000015258789,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.05590000003576279,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.05570000037550926,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.8044000267982483},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6248000264167786},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5946000218391418},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.573199987411499},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.46459999680519104},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.4124000072479248},{"id":"https://openalex.org/keywords/bayesian-network","display_name":"Bayesian network","score":0.4016000032424927}],"concepts":[{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.8044000267982483},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7055000066757202},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6248000264167786},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5946000218391418},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.573199987411499},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5238999724388123},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.46459999680519104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45910000801086426},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.4124000072479248},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.4016000032424927},{"id":"https://openalex.org/C82142266","wikidata":"https://www.wikidata.org/wiki/Q3456604","display_name":"Dynamic Bayesian network","level":3,"score":0.3644999861717224},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.36390000581741333},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3346000015735626},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2809000015258789},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27970001101493835},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.25920000672340393},{"id":"https://openalex.org/C3020402766","wikidata":"https://www.wikidata.org/wiki/Q104376712","display_name":"Prior information","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2601.19794","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.19794","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2601.19794","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.19794","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"transition":[1],"from":[2],"monolithic":[3],"to":[4,17,40,51,66],"multi-component":[5],"neural":[6,10],"architectures":[7],"in":[8,102],"advanced":[9],"network":[11],"controllers":[12],"poses":[13],"substantial":[14],"challenges":[15],"due":[16],"the":[18,23,42,92],"high":[19],"computational":[20],"complexity":[21,30],"of":[22,45],"latter.":[24],"Conventional":[25],"model":[26],"compression":[27,112],"techniques":[28],"for":[29],"reduction,":[31],"such":[32],"as":[33],"structured":[34],"pruning":[35,60],"based":[36],"on":[37],"norm-based":[38],"metrics":[39,71],"estimate":[41],"relative":[43],"importance":[44,70,103],"distinct":[46,69],"parameter":[47],"groups,":[48],"often":[49,107],"fail":[50],"capture":[52],"functional":[53],"significance.":[54],"This":[55],"paper":[56],"introduces":[57],"a":[58,87],"component-aware":[59],"framework":[61,94],"that":[62,91,104],"utilizes":[63],"gradient":[64],"information":[65],"compute":[67],"three":[68],"during":[72],"training:":[73],"Gradient":[74],"Accumulation,":[75],"Fisher":[76],"Information,":[77],"and":[78,86,99],"Bayesian":[79],"Uncertainty.":[80],"Experimental":[81],"results":[82],"with":[83],"an":[84],"autoencoder":[85],"TD-MPC":[88],"agent":[89],"demonstrate":[90],"proposed":[93],"reveals":[95],"critical":[96],"structural":[97],"dependencies":[98],"dynamic":[100],"shifts":[101],"static":[105],"heuristics":[106],"miss,":[108],"supporting":[109],"more":[110],"informed":[111],"decisions.":[113]},"counts_by_year":[],"updated_date":"2026-08-16T07:02:28.622633","created_date":"2026-01-29T00:00:00"}