{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T14:42:29Z","timestamp":1787323349438,"version":"build-2736575974"},"reference-count":85,"publisher":"Society for Industrial & Applied Mathematics (SIAM)","issue":"3","funder":[{"name":"Hong Kong Research Grant Council"},{"DOI":"10.13039\/501100017607","name":"Shenzhen Fundamental Research Program","doi-asserted-by":"crossref","award":["JCYJ20220530164812027"],"award-info":[{"award-number":["JCYJ20220530164812027"]}],"id":[{"id":"10.13039\/501100017607","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Sichuan Science and Technology Program","award":["2021YFS0374"],"award-info":[{"award-number":["2021YFS0374"]}]},{"name":"Sichuan Science and Technology Program","award":["2022YFS0600"],"award-info":[{"award-number":["2022YFS0600"]}]},{"name":"Hong Kong Research Grant Council","award":["17201020"],"award-info":[{"award-number":["17201020"]}]},{"name":"Hong Kong Research Grant Council","award":["17300021"],"award-info":[{"award-number":["17300021"]}]},{"name":"Hong Kong Research Grant Council","award":["C7004-21GF"],"award-info":[{"award-number":["C7004-21GF"]}]},{"name":"NSFC-RGC","award":["N-HKU76921"],"award-info":[{"award-number":["N-HKU76921"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2682023CX069"],"award-info":[{"award-number":["2682023CX069"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12201522"],"award-info":[{"award-number":["12201522"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["SIAM J. Imaging Sci."],"published-print":{"date-parts":[[2024,9,30]]},"abstract":"<jats:p>Abstract.<\/jats:p>\n                  <jats:p>This paper studies quantized corrupted sensing where the measurements are contaminated by unknown corruption and then quantized by a dithered uniform quantizer. We establish uniform guarantees for Lasso that ensure the accurate recovery of all signals and corruptions using a single draw of the sub-Gaussian sensing matrix and uniform dither. For signal and corruption with structured priors (e.g., sparsity, low-rankness), our uniform error rate for constrained Lasso typically coincides with the nonuniform one up to logarithmic factors, indicating that the uniformity costs very little. By contrast, our uniform error rate for unconstrained Lasso exhibits worse dependence on the structured parameters due to regularization parameters larger than the ones for nonuniform recovery. These results complement the nonuniform ones recently obtained in Sun, Cui, and Liu [ IEEE Trans. Signal Process., 70 (2022), pp. 600\u2013615] and provide more insights for understanding actual applications where the sensing ensemble is typically fixed and the corruption may be adversarial. For signal and corruption living in the ranges of some Lipschitz continuous generative models (referred to as generative priors), we achieve uniform recovery via constrained Lasso with a measurement number proportional to the latent dimensions of the generative models. We present experimental results to corroborate our theories. From the technical side, our treatments to the two kinds of priors are (nearly) unified and share the common key ingredients of a (global) quantized product embedding (QPE) property, which states that the dithered uniform quantization (universally) preserves the inner product. As a by-product, our QPE result refines the one in Xu and Jacques [ Inf. Inference, 9 (2020), pp. 543\u2013586] under the sub-Gaussian random matrix, and in this specific instance, we are able to sharpen the uniform error decaying rate (for the projected back-projection estimator with signals in some convex symmetric set) presented therein from [Formula: see text] to [Formula: see text].<\/jats:p>","DOI":"10.1137\/23m1578358","type":"journal-article","created":{"date-parts":[[2024,9,17]],"date-time":"2024-09-17T12:41:06Z","timestamp":1726576866000},"page":"1909-1977","source":"Crossref","is-referenced-by-count":1,"title":["Uniform Recovery Guarantees for Quantized Corrupted Sensing Using Structured or Generative Priors"],"prefix":"10.1137","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3606-9598","authenticated-orcid":true,"given":"Junren","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Mathematics, The University of Hong Kong, Hong Kong, People\u2019s Republic of China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0392-6648","authenticated-orcid":true,"given":"Zhaoqiang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, People\u2019s Republic of China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Ding","sequence":"additional","affiliation":[{"name":"School of Mathematics, Southwest Jiaotong University, Chengdu 611756, People\u2019s Republic of China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6833-5227","authenticated-orcid":true,"given":"Michael K.","family":"Ng","sequence":"additional","affiliation":[{"name":"Department of Mathematics, Hong Kong Baptist University, Hong Kong, People\u2019s Republic of China."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"351","published-online":{"date-parts":[[2024,9,17]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s00365-007-9003-x"},{"key":"ref2","volume-title":"Foundations of Image Science","author":"Barrett H. H.","year":"2013"},{"key":"ref3","unstructured":"A. Berk, Deep Generative Demixing: Recovering Lipschitz Signals from Noisy Subgaussian Mixtures, preprint, arXiv:2010.06652, 2020."},{"key":"ref4","doi-asserted-by":"crossref","unstructured":"A. Berk, Deep generative demixing: Error bounds for demixing subgaussian mixtures of Lipschitz signals, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, New York, 2021, pp. 4010\u20134014.","DOI":"10.1109\/ICASSP39728.2021.9413573"},{"key":"ref5","unstructured":"A. Bora, A. Jalal, E. Price, and A. G. Dimakis, Compressed sensing using generative models, in International Conference on Machine Learning, PMLR, 2017, pp. 537\u2013546."},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780199535255.001.0001"},{"key":"ref7","doi-asserted-by":"crossref","unstructured":"P. T. Boufounos and R. G. Baraniuk, 1-bit compressive sensing, in Annual Conference on Information Sciences and Systems, IEEE, New York, 2008, pp. 16\u201321.","DOI":"10.1109\/CISS.2008.4558487"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16042-9_7"},{"key":"ref9","first-page":"3619","volume":"14","author":"Cai T.","year":"2013","journal-title":"J. Mach. Learn. Res."},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1970392.1970395"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2011.2111771"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2005.862083"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1137\/090761793"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2018.2890194"},{"key":"ref15","doi-asserted-by":"crossref","unstructured":"J. Chen and M. K. Ng, A Parameter-Free Two-Bit Covariance Estimator with Improved Operator Norm Error Rate, preprint, arXiv:2308.16059, 2023.","DOI":"10.2139\/ssrn.4585384"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2023.3293830"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2023.3329240"},{"key":"ref18","doi-asserted-by":"crossref","unstructured":"J. Chen, J. Scarlett, M. K. Ng, and Z. Liu, A unified framework for uniform signal recovery in nonlinear generative compressed sensing, in 37th Conference on Neural Information Processing Systems, 2023, https:\/\/openreview.net\/forum?id=vUXNNLatFv.","DOI":"10.52202\/075280-0361"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2023.3266271"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2023.3322813"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2013.2249572"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1093\/imaiai\/iau006"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-015-9280-x"},{"key":"ref24","doi-asserted-by":"crossref","unstructured":"S. Dirksen, Quantized compressed sensing: A survey, in Compressed Sensing and Its Applications: Third International MATHEON Conference 2017, Springer-Verlag, Berlin, 2019, pp. 67\u201395.","DOI":"10.1007\/978-3-319-73074-5_2"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2024.3358994"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1214\/22-AOS2239"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.4171\/jems\/1066"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2006.871582"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/42.993128"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.57"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2010.936726"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-8176-4948-7_1"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2013.2293654"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-09745-4_2"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2016.2642993"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-022-09562-y"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/18.720541"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/18.256489"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0930-5"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2021.3105359"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2007.914732"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2012.2234823"},{"key":"ref43","first-page":"14938","volume":"34","author":"Jalal A.","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1972.tb02653.x"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.22024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2021.3070789"},{"key":"ref47","unstructured":"A. Kamath, E. Price, and S. Karmalkar, On the power of compressed sensing with generative models, in International Conference on Machine Learning, PMLR, 2020, pp. 5101\u20135109."},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s00365-012-9176-9"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-45282-1_18"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1969.tb01187.x"},{"key":"ref52","doi-asserted-by":"crossref","unstructured":"Z. Liu, S. Gomes, A. Tiwari, and J. Scarlett, Sample complexity bounds for 1-bit compressive sensing and binary stable embeddings with generative priors, in International Conference on Machine Learning, PMLR, 2020, pp. 6216\u20136225.","DOI":"10.1109\/SPCOM50965.2020.9179594"},{"key":"ref53","volume-title":"International Conference on Learning Representations","author":"Liu Z.","year":"2022"},{"key":"ref54","doi-asserted-by":"crossref","unstructured":"Z. Liu, P. Luo, X. Wang, and X. Tang, Deep learning face attributes in the wild, in Proceedings of the IEEE International Conference on Computer Vision, IEEE, New York, 2015, pp. 3730\u20133738.","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref55","first-page":"19125","volume":"33","author":"Liu Z.","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2020.2980676"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-014-9191-2"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.spa.2016.04.019"},{"key":"ref59","first-page":"1665","volume":"13","author":"Negahban S.","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1214\/12-STS400"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2012.2232347"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2013.2240435"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2020.2991563"},{"key":"ref64","unstructured":"S. Oymak and B. Recht, Near-Optimal Bounds for Binary Embeddings of Arbitrary Sets, preprint, arXiv:1512.04433, 2015."},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2012.2207945"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.21442"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2016.2517008"},{"key":"ref68","first-page":"1","volume":"6","author":"Plan Y.","year":"2017","journal-title":"Inf. Inference"},{"key":"ref69","unstructured":"S. Qiu, X. Wei, and Z. Yang, Robust one-bit recovery via ReLU generative networks: Near-optimal statistical rate and global landscape analysis, in International Conference on Machine Learning, PMLR, 2020, pp. 7857\u20137866."},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2820120"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00570"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1214\/18-AOS1725"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1964.1088973"},{"key":"ref74","first-page":"4609","volume-title":"International Conference on Acoustics, Speech, and Signal Processing","author":"Shah V.","year":"2018"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2022.3141884"},{"key":"ref76","author":"Tachella J.","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2020.2965733"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1017\/9781108231596"},{"key":"ref79","doi-asserted-by":"crossref","unstructured":"B. Widrow and I. Koll\u00e1r, Quantization Noise: Roundoff Error in Digital Computation, Signal Processing, Control, and Communications, Cambridge University Press, Cambridge, 2008.","DOI":"10.1017\/CBO9780511754661"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.79"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1093\/imaiai\/iaz021"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2012.2212415"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2023.3317906"},{"key":"ref84","first-page":"2481","volume":"21","author":"Yu G.","year":"2011","journal-title":"IEEE Trans. Image Process."},{"key":"ref85","unstructured":"H. Zhang, J. Li, K. Kara, D. Alistarh, J. Liu, and C. Zhang, ZipML: Training linear models with end-to-end low precision, and a little bit of deep learning, in International Conference on Machine Learning, PMLR, 2017, pp. 4035\u20134043."}],"container-title":["SIAM Journal on Imaging Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/epubs.siam.org\/doi\/pdf\/10.1137\/23M1578358","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T13:57:12Z","timestamp":1787320632000},"score":1,"resource":{"primary":{"URL":"https:\/\/epubs.siam.org\/doi\/10.1137\/23M1578358"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,17]]},"references-count":85,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,9,30]]}},"alternative-id":["10.1137\/23M1578358"],"URL":"https:\/\/doi.org\/10.1137\/23m1578358","relation":{},"ISSN":["1936-4954"],"issn-type":[{"value":"1936-4954","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,17]]}}}