{"id":"https://openalex.org/W7147085444","doi":"https://doi.org/10.48550/arxiv.2603.29034","title":"The Surprising Effectiveness of Noise Pretraining for Implicit Neural Representations","display_name":"The Surprising Effectiveness of Noise Pretraining for Implicit Neural Representations","publication_year":2026,"publication_date":"2026-03-30","ids":{"openalex":"https://openalex.org/W7147085444","doi":"https://doi.org/10.48550/arxiv.2603.29034"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.29034","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29034","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.29034","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084629908","display_name":"Kushal Vyas","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Vyas, Kushal","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132727175","display_name":"Alper Kayabasi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kayabasi, Alper","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132557336","display_name":"Daniel Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Daniel","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130654587","display_name":"Vishwanath Saragadam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saragadam, Vishwanath","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073971393","display_name":"Ashok Veeraraghavan","orcid":"https://orcid.org/0000-0001-5043-7460"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Veeraraghavan, Ashok","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130437034","display_name":"Guha Balakrishnan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Balakrishnan, Guha","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5084629908"],"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.17589999735355377,"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"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.17589999735355377,"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/T11094","display_name":"Face Recognition and Perception","score":0.1509999930858612,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.06840000301599503,"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/initialization","display_name":"Initialization","score":0.8554999828338623},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.7669000029563904},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.6945000290870667},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6927000284194946},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5309000015258789},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5148000121116638},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.41609999537467957},{"id":"https://openalex.org/keywords/stochastic-resonance","display_name":"Stochastic resonance","score":0.4140999913215637},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.40799999237060547}],"concepts":[{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.8554999828338623},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.7669000029563904},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6965000033378601},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6945000290870667},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6927000284194946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6118000149726868},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5309000015258789},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5148000121116638},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.41609999537467957},{"id":"https://openalex.org/C207658827","wikidata":"https://www.wikidata.org/wiki/Q1999781","display_name":"Stochastic resonance","level":4,"score":0.4140999913215637},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41119998693466187},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.40799999237060547},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.4007999897003174},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.353300005197525},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3271999955177307},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.3190000057220459},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C2986577269","wikidata":"https://www.wikidata.org/wiki/Q11306265","display_name":"Random noise","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29280000925064087},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2842000126838684},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25429999828338623},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.29034","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29034","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.29034","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29034","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"approximation":[1],"and":[2,82,91,104,162],"convergence":[3],"properties":[4],"of":[5,64,152,159],"implicit":[6],"neural":[7],"representations":[8],"(INRs)":[9],"are":[10],"known":[11],"to":[12,16,86,124],"be":[13],"highly":[14],"sensitive":[15],"parameter":[17],"initialization":[18,23,173],"strategies.":[19],"While":[20],"several":[21],"data-driven":[22,172],"methods":[24],"demonstrate":[25],"significant":[26],"improvements":[27],"over":[28],"standard":[29],"random":[30],"sampling,":[31],"the":[32,147,170],"reasons":[33],"for":[34,94,137],"their":[35,84],"success":[36],"--":[37,50],"specifically,":[38],"whether":[39],"they":[40],"encode":[41,92],"classical":[42],"statistical":[43],"signal":[44,120,160],"priors":[45,93,136],"or":[46],"more":[47,178,190],"complex":[48],"features":[49],"remain":[51],"poorly":[52],"understood.":[53],"In":[54,139],"this":[55,59],"study,":[56],"we":[57,141],"explore":[58],"phenomenon":[60],"through":[61],"a":[62,108],"series":[63],"experimental":[65],"analyses":[66,101],"leveraging":[67],"noise":[68,75,115,130,145],"pretraining.":[69],"We":[70],"pretrain":[71],"INRs":[72],"on":[73,102,113,167],"diverse":[74],"classes":[76],"(e.g.,":[77],"Gaussian,":[78],"Dead":[79],"Leaves,":[80],"Spectral)":[81],"measure":[83],"ability":[85],"both":[87],"fit":[88],"unseen":[89],"signals":[90],"an":[95,156],"inverse":[96,163],"imaging":[97,164],"task":[98],"(denoising).":[99],"Our":[100],"image":[103,135],"video":[105],"data":[106],"reveal":[107],"surprising":[109],"finding:":[110],"simply":[111],"pretraining":[112],"unstructured":[114,129],"(Uniform,":[116],"Gaussian)":[117],"dramatically":[118],"improves":[119],"fitting":[121,161],"capacity":[122],"compared":[123],"all":[125],"other":[126],"baselines.":[127],"However,":[128],"also":[131,142],"yields":[132],"poor":[133],"deep":[134],"denoising.":[138],"contrast,":[140],"find":[143],"that":[144],"with":[146,169],"classic":[148],"$1/|f^\u03b1|$":[149],"spectral":[150],"structure":[151],"natural":[153],"images":[154],"achieves":[155],"excellent":[157],"balance":[158],"capabilities,":[165],"performing":[166],"par":[168],"best":[171],"methods.":[174],"This":[175],"finding":[176],"enables":[177],"efficient":[179],"INR":[180],"training":[181],"in":[182],"applications":[183],"lacking":[184],"sufficient":[185],"prior":[186],"domain-specific":[187],"data.":[188],"For":[189],"details,":[191],"visit":[192],"project":[193],"page":[194],"at":[195],"https://kushalvyas.github.io/noisepretraining.html":[196]},"counts_by_year":[],"updated_date":"2026-04-02T13:53:19.096889","created_date":"2026-04-02T00:00:00"}