{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T22:45:08Z","timestamp":1781131508138,"version":"3.54.1"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Austrian Federal Ministry for Digital and Economic Affairs"},{"DOI":"10.13039\/100010132","name":"\u00d6sterreichische Nationalstiftung f\u00fcr Forschung, Technologie und Entwicklung","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010132","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006012","name":"Christian Doppler Forschungsgesellschaft","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006012","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Technical University (TU) Wien Bibliothek"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3439850","type":"journal-article","created":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T17:53:24Z","timestamp":1723053204000},"page":"109847-109860","source":"Crossref","is-referenced-by-count":5,"title":["Conformal Prediction Based Confidence for Latency Estimation of DNN Accelerators: A Black-Box Approach"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1877-4114","authenticated-orcid":false,"given":"Matthias","family":"Wess","sequence":"first","affiliation":[{"name":"Institute of Computer Technology, TU Wien, Vienna, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5834-6526","authenticated-orcid":false,"given":"Daniel","family":"Schn\u00f6ll","sequence":"additional","affiliation":[{"name":"Institute of Computer Technology, TU Wien, Vienna, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4789-2375","authenticated-orcid":false,"given":"Dominik","family":"Dallinger","sequence":"additional","affiliation":[{"name":"Institute of Computer Technology, TU Wien, Vienna, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8022-2232","authenticated-orcid":false,"given":"Matthias","family":"Bittner","sequence":"additional","affiliation":[{"name":"Institute of Computer Technology, TU Wien, Vienna, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2251-0004","authenticated-orcid":false,"given":"Axel","family":"Jantsch","sequence":"additional","affiliation":[{"name":"Institute of Computer Technology, TU Wien, Vienna, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"ProxylessNAS: Direct neural architecture search on target task and hardware","volume-title":"Proc. ICLR","author":"Cai"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/HPCS48598.2019.9188213"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3101936"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3047259"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.11.043"},{"key":"ref7","article-title":"PerfSAGE: Generalized inference performance predictor for arbitrary deep learning models on edge devices","author":"Chai","year":"2023","journal-title":"arXiv:2301.10999"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3458864.3467882"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IGSC55832.2022.9969374"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.05.002"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3205410"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3276937"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-SEIP58684.2023.00039"},{"key":"ref14","article-title":"BRP-NAS: Prediction-based NAS using GCNs","author":"Dudziak","year":"2020","journal-title":"arXiv:2007.08668"},{"key":"ref15","article-title":"Once-for-all: Train one network and specialize it for efficient deployment","volume-title":"Proc. ICLR","author":"Cai"},{"key":"ref16","article-title":"HELP: Hardware-adaptive efficient latency prediction for NAS via meta-learning","author":"Lee","year":"2021","journal-title":"arXiv:2106.08630"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CASES55004.2022.00020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.23919\/DATE54114.2022.9774728"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MILCOM52596.2021.9652907"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00410"},{"key":"ref21","article-title":"MAPLE-X: Latency prediction with explicit microprocessor prior knowledge","author":"Abbasi","year":"2022","journal-title":"arXiv:2205.12660"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS54860.2022.00092"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26102"},{"key":"ref24","first-page":"3","article-title":"DIPPM: A deep learning inference performance predictive model using graph neural networks","volume-title":"Proc. Euro-Par","author":"Selvam"},{"key":"ref25","first-page":"148","article-title":"Learning by transduction","volume-title":"Proc. UAI","author":"Gammerman"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/b106715"},{"key":"ref27","first-page":"983","article-title":"Quantile regression forests","volume":"7","author":"Meinshausen","year":"2006","journal-title":"J. Mach. Learn. Res."},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2009.12.015"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.bjpt.2018.12.006"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-014-5453-0"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s10472-017-9539-9"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i11.21459"},{"key":"ref34","first-page":"62","article-title":"Conformal prediction for automatic face recognition","volume-title":"Proc. COPA","volume":"60","author":"Eliades"},{"key":"ref35","first-page":"285","article-title":"Application of conformal prediction interval estimations to market makers\u2019 net positions","volume-title":"Proc. COPA","volume":"128","author":"Wisniewski"},{"key":"ref36","volume-title":"ARM Ethos NPU Technical Reference Manual","year":"2024"},{"key":"ref37","first-page":"12292","article-title":"Conformal prediction sets for graph neural networks","volume-title":"Proc. ICML","volume":"202","author":"Zargarbashi"},{"key":"ref38","first-page":"24","article-title":"crepes: A Python package for generating conformal regressors and predictive systems","volume-title":"Proc. COPA","volume":"179","author":"Bostr\u00f6m"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10630545.pdf?arnumber=10630545","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T17:43:17Z","timestamp":1723743797000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10630545\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3439850","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}