{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T21:51:40Z","timestamp":1791323500501,"version":"4.3.1"},"reference-count":106,"publisher":"Institute of Mathematical Statistics","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Ann. Statist."],"published-print":{"date-parts":[[2026,8,1]]},"abstract":"<jats:p>Characterizing the distribution of high-dimensional statistical estimators is a challenging task, due to the breakdown of classical asymptotic theory in high dimension. This paper makes progress towards this by developing non-asymptotic distributional characterizations for approximate message passing (AMP)\u2014a family of iterative algorithms that prove effective as both fast estimators and powerful theoretical machinery\u2014for both sparse and robust regression. Prior AMP theory, which focused on high-dimensional asymptotics for the most part, failed to describe the behavior of AMP when the number of iterations exceeds o(logn\/loglogn) (with n the sample size). Our AMP theory is further leveraged to derive a refined rate for the Lasso estimator, built upon a nonasymptotic convergence of AMP to Lasso. To the best of our knowledge, this is the first result of its kind, breaking the rate barrier resulting from the widely adopted Gaussian min-max theorem. Our results establish approximate accuracy of Gaussian approximation of the AMP iterates, which improves upon prior results and implies enhanced distributional characterizations for both optimally tuned Lasso and robust M-estimator.<\/jats:p>","DOI":"10.1214\/25-aos2612","type":"journal-article","created":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T08:10:45Z","timestamp":1787040645000},"page":"1655-1681","source":"Crossref","is-referenced-by-count":0,"title":["A nonasymptotic distributional theory of approximate message passing for sparse and robust regression"],"prefix":"10.1214","volume":"54","author":[{"given":"Gen","family":"Li","sequence":"first","affiliation":[{"name":"Department of Statistics and Data Science, Chinese University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuting","family":"Wei","sequence":"additional","affiliation":[{"name":"Department of Statistics and Data Science, the Wharton School, University of Pennsylvania"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"108","reference":[{"key":"6","doi-asserted-by":"publisher","unstructured":"<small>Bayati, M.<\/small> and <small>Montanari, A.<\/small> (2011). The dynamics of message passing on dense graphs, with applications to compressed sensing. <i>IEEE Trans. Inf. Theory<\/i> <b>57<\/b> 764\u2013785.","DOI":"10.1109\/TIT.2010.2094817"},{"key":"31","doi-asserted-by":"publisher","unstructured":"<small>Deshpande, Y.<\/small>, <small>Abbe, E.<\/small> and <small>Montanari, A.<\/small> (2017). Asymptotic mutual information for the balanced binary stochastic block model. <i>Inf. Inference<\/i> <b>6<\/b> 125\u2013170.","DOI":"10.1093\/imaiai\/iaw017"},{"key":"37","doi-asserted-by":"crossref","unstructured":"<small>Donoho, D. L.<\/small>, <small>Maleki, A.<\/small> and <small>Montanari, A.<\/small> (2009). Message-passing algorithms for compressed sensing. <i>Proc. Natl. Acad. Sci. USA<\/i> <b>106<\/b> 18914\u201318919.","DOI":"10.1073\/pnas.0909892106"},{"key":"54","doi-asserted-by":"publisher","unstructured":"<small>Javanmard, A.<\/small> and <small>Montanari, A.<\/small> (2013). State evolution for general approximate message passing algorithms, with applications to spatial coupling. <i>Inf. Inference<\/i> <b>2<\/b> 115\u2013144.","DOI":"10.1093\/imaiai\/iat004"},{"key":"98","doi-asserted-by":"publisher","unstructured":"<small>Xia, D.<\/small> and <small>Yuan, M.<\/small> (2021). Statistical inferences of linear forms for noisy matrix completion. <i>J. R. Stat. Soc. Ser. B. Stat. Methodol.<\/i> <b>83<\/b> 58\u201377.","DOI":"10.1111\/rssb.12400"},{"key":"59","doi-asserted-by":"publisher","unstructured":"<small>Lei, L.<\/small>, <small>Bickel, P. J.<\/small> and <small>El Karoui, N.<\/small> (2018). Asymptotics for high dimensional regression <i>M<\/i>-estimates: Fixed design results. <i>Probab. Theory Related Fields<\/i> <b>172<\/b> 983\u20131079.","DOI":"10.1007\/s00440-017-0824-7"},{"key":"52","doi-asserted-by":"publisher","unstructured":"<small>Huber, P. J.<\/small> (1964). Robust Estimation of a Location Parameter. <i>Ann. Math. Statist.<\/i> <b>35<\/b> 73\u2013101.","DOI":"10.1214\/aoms\/1177703732"},{"key":"58","unstructured":"<small>LE CAM, L.<\/small> (2012). <i>Asymptotic Methods in Statistical Decision Theory<\/i>. <i>Springer Series in Statistics<\/i>. Springer, New York."},{"key":"95","doi-asserted-by":"publisher","unstructured":"<small>WAINWRIGHT, M. J.<\/small> (2009). Sharp thresholds for high-dimensional and noisy sparsity recovery using <math xmlns=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" overflow=\"scroll\" id=\"eq_7\"><msub><mrow><mi>\u2113<\/mi><\/mrow><mrow><mn>1<\/mn><\/mrow><\/msub><\/math>-constrained quadratic programming (Lasso). <i>IEEE Trans. Inf. Theory<\/i> <b>55<\/b> 2183\u20132202.","DOI":"10.1109\/TIT.2009.2016018"},{"key":"11","doi-asserted-by":"publisher","unstructured":"<small>BELLEC, P. C.<\/small> and <small>ZHANG, C.-H.<\/small> (2023). Debiasing convex regularized estimators and interval estimation in linear models. <i>Ann. Statist.<\/i> <b>51<\/b> 391\u2013436.","DOI":"10.1214\/22-aos2243"},{"key":"56","doi-asserted-by":"publisher","unstructured":"<small>Javanmard, A.<\/small> and <small>Montanari, A.<\/small> (2018). Debiasing the Lasso: Optimal sample size for Gaussian designs. <i>Ann. Statist.<\/i> <b>46<\/b> 2593\u20132622.","DOI":"10.1214\/17-AOS1630"},{"key":"2","doi-asserted-by":"publisher","unstructured":"<small>Amelunxen, D.<\/small>, <small>Lotz, M.<\/small>, <small>McCoy, M. B.<\/small> and <small>Tropp, J. A.<\/small> (2014). Living on the edge: Phase transitions in convex programs with random data. <i>Inf. Inference<\/i> <b>3<\/b> 224\u2013294.","DOI":"10.1093\/imaiai\/iau005"},{"key":"7","doi-asserted-by":"publisher","unstructured":"<small>Bayati, M.<\/small> and <small>Montanari, A.<\/small> (2012). The LASSO risk for Gaussian matrices. <i>IEEE Trans. Inf. Theory<\/i> <b>58<\/b> 1997\u20132017.","DOI":"10.1109\/TIT.2011.2174612"},{"key":"41","doi-asserted-by":"publisher","unstructured":"<small>El Karoui, N.<\/small> (2018). On the impact of predictor geometry on the performance on high-dimensional ridge-regularized generalized robust regression estimators. <i>Probab. Theory Related Fields<\/i> <b>170<\/b> 95\u2013175.","DOI":"10.1007\/s00440-016-0754-9"},{"key":"85","doi-asserted-by":"publisher","unstructured":"<small>Schniter, P.<\/small> and <small>Rangan, S.<\/small> (2015). Compressive phase retrieval via generalized approximate message passing. <i>IEEE Trans. Signal Process.<\/i> <b>63<\/b> 1043\u20131055.","DOI":"10.1109\/TSP.2014.2386294"},{"key":"90","doi-asserted-by":"publisher","unstructured":"<small>Thrampoulidis, C.<\/small>, <small>Abbasi, E.<\/small> and <small>Hassibi, B.<\/small> (2018). Precise error analysis of regularized <i>M<\/i>-estimators in high dimensions. <i>IEEE Trans. Inf. Theory<\/i> <b>64<\/b> 5592\u20135628.","DOI":"10.1109\/TIT.2018.2840720"},{"key":"49","doi-asserted-by":"crossref","unstructured":"<small>Hampel, F. R.<\/small> (1974). The influence curve and its role in robust estimation. <i>J. Amer. Statist. Assoc.<\/i> <b>69<\/b> 383\u2013393.","DOI":"10.1080\/01621459.1974.10482962"},{"key":"28","doi-asserted-by":"publisher","unstructured":"<small>Chen, Y.<\/small>, <small>Fan, J.<\/small>, <small>Ma, C.<\/small> and <small>Yan, Y.<\/small> (2019b). Inference and uncertainty quantification for noisy matrix completion. <i>Proc. Natl. Acad. Sci. USA<\/i> <b>116<\/b> 22931\u201322937.","DOI":"10.1073\/pnas.1910053116"},{"key":"5","doi-asserted-by":"publisher","unstructured":"<small>Bayati, M.<\/small>, <small>Lelarge, M.<\/small> and <small>Montanari, A.<\/small> (2015). Universality in polytope phase transitions and message passing algorithms. <i>Ann. Appl. Probab.<\/i> <b>25<\/b> 753\u2013822.","DOI":"10.1214\/14-AAP1010"},{"key":"73","doi-asserted-by":"publisher","unstructured":"<small>MITCHELL, T. J.<\/small> and <small>BEAUCHAMP, J. J.<\/small> (1988). Bayesian variable selection in linear regression. <i>J. Amer. Statist. Assoc.<\/i> <b>83<\/b> 1023\u20131036.","DOI":"10.1080\/01621459.1988.10478694"},{"key":"4","doi-asserted-by":"publisher","unstructured":"<small>BARBIER, J.<\/small>, <small>KRZAKALA, F.<\/small>, <small>MACRIS, N.<\/small>, <small>MIOLANE, L.<\/small> and <small>ZDEBOROV\u00c1, L.<\/small> (2019). Optimal errors and phase transitions in high-dimensional generalized linear models. <i>Proc. Natl. Acad. Sci. USA<\/i> <b>116<\/b> 5451\u20135460.","DOI":"10.1073\/pnas.1802705116"},{"key":"15","doi-asserted-by":"publisher","unstructured":"<small>BU, Z.<\/small>, <small>KLUSOWSKI, J. M.<\/small>, <small>RUSH, C.<\/small> and <small>SU, W. J.<\/small> (2021). Algorithmic analysis and statistical estimation of SLOPE via approximate message passing. <i>IEEE Trans. Inf. Theory<\/i> <b>67<\/b> 506\u2013537.","DOI":"10.1109\/TIT.2020.3025272"},{"key":"72","doi-asserted-by":"publisher","unstructured":"<small>MIOLANE, L.<\/small> and <small>MONTANARI, A.<\/small> (2021). The distribution of the Lasso: Uniform control over sparse balls and adaptive parameter tuning. <i>Ann. Statist.<\/i> <b>49<\/b> 2313\u20132335.","DOI":"10.1214\/20-aos2038"},{"key":"36","doi-asserted-by":"publisher","unstructured":"<small>DONOHO, D. L.<\/small>, <small>JAVANMARD, A.<\/small> and <small>MONTANARI, A.<\/small> (2013). Information-theoretically optimal compressed sensing via spatial coupling and approximate message passing. <i>IEEE Trans. Inf. Theory<\/i> <b>59<\/b> 7434\u20137464.","DOI":"10.1109\/TIT.2013.2274513"},{"key":"69","doi-asserted-by":"publisher","unstructured":"<small>MALEKI, A.<\/small>, <small>ANITORI, L.<\/small>, <small>YANG, Z.<\/small> and <small>BARANIUK, R. G.<\/small> (2013). Asymptotic analysis of complex LASSO via complex approximate message passing (CAMP). <i>IEEE Trans. Inf. Theory<\/i> <b>59<\/b> 4290\u20134308.","DOI":"10.1109\/TIT.2013.2252232"},{"key":"76","doi-asserted-by":"publisher","unstructured":"<small>MONTANARI, A.<\/small> and <small>VENKATARAMANAN, R.<\/small> (2021). Estimation of low-rank matrices via approximate message passing. <i>Ann. Statist.<\/i> <b>49<\/b> 321\u2013345.","DOI":"10.1214\/20-AOS1958"},{"key":"80","doi-asserted-by":"crossref","unstructured":"<small>RANGAN, S.<\/small> and <small>FLETCHER, A. K.<\/small> (2012). Iterative estimation of constrained rank-one matrices in noise. In 2012 <i>IEEE International Symposium on Information Theory Proceedings<\/i> 1246\u20131250. IEEE.","DOI":"10.1109\/ISIT.2012.6283056"},{"key":"45","unstructured":"<small>FAN, J.<\/small>, <small>LI, R.<\/small>, <small>ZHANG, C.-H.<\/small> and <small>ZOU, H.<\/small> (2020). <i>Statistical Foundations of Data Science<\/i>. CRC Press, Boca Raton."},{"key":"83","doi-asserted-by":"publisher","unstructured":"<small>RUDELSON, M.<\/small> and <small>VERSHYNIN, R.<\/small> (2008). On sparse reconstruction from Fourier and Gaussian measurements. <i>Comm. Pure Appl. Math.<\/i> <b>61<\/b> 1025\u20131045.","DOI":"10.1002\/cpa.20227"},{"key":"10","doi-asserted-by":"publisher","unstructured":"<small>BELLEC, P. C.<\/small> and <small>ZHANG, C.-H.<\/small> (2022). De-biasing the lasso with degrees-of-freedom adjustment. <i>Bernoulli<\/i> <b>28<\/b> 713\u2013743.","DOI":"10.3150\/21-BEJ1348"},{"key":"26","doi-asserted-by":"publisher","unstructured":"<small>CHEN, W.-K.<\/small> and <small>LAM, W.-K.<\/small> (2021). Universality of approximate message passing algorithms. <i>Electron. J. Probab.<\/i> <b>26<\/b> Paper No. 36, 44 pp.","DOI":"10.1214\/21-EJP604"},{"key":"84","doi-asserted-by":"publisher","unstructured":"<small>RUSH, C.<\/small> and <small>VENKATARAMANAN, R.<\/small> (2018). Finite sample analysis of approximate message passing algorithms. <i>IEEE Trans. Inf. Theory<\/i> <b>64<\/b> 7264\u20137286.","DOI":"10.1109\/TIT.2018.2816681"},{"key":"70","doi-asserted-by":"crossref","unstructured":"<small>MARONNA, R. A.<\/small>, <small>MARTIN, R. D.<\/small>, <small>YOHAI, V. J.<\/small> and <small>SALIBI\u00c1N-BARRERA, M.<\/small> (2019). <i>Robust Statistics<\/i>: <i>Theory and Methods<\/i> (<i>with R<\/i>). <i>Wiley Series in Probability and Statistics<\/i>. Wiley, Hoboken, NJ.","DOI":"10.1002\/9781119214656"},{"key":"46","doi-asserted-by":"publisher","unstructured":"<small>FAN, Z.<\/small> (2022). Approximate message passing algorithms for rotationally invariant matrices. <i>Ann. Statist.<\/i> <b>50<\/b> 197\u2013224.","DOI":"10.1214\/21-aos2101"},{"key":"93","doi-asserted-by":"publisher","unstructured":"<small>van der Vaart, A. W.<\/small> (1998). <i>Asymptotic Statistics<\/i>. <i>Cambridge Series in Statistical and Probabilistic Mathematics<\/i> <b>3<\/b>. Cambridge Univ. Press, Cambridge.","DOI":"10.1017\/CBO9780511802256"},{"key":"44","doi-asserted-by":"publisher","unstructured":"<small>Fan, J.<\/small> and <small>Li, R.<\/small> (2001). Variable selection via nonconcave penalized likelihood and its oracle properties. <i>J. Amer. Statist. Assoc.<\/i> <b>96<\/b> 1348\u20131360.","DOI":"10.1198\/016214501753382273"},{"key":"106","doi-asserted-by":"publisher","unstructured":"<small>Zou, H.<\/small> and <small>Hastie, T.<\/small> (2005). Regularization and variable selection via the elastic net. <i>J. R. Stat. Soc. Ser. B. Stat. Methodol.<\/i> <b>67<\/b> 301\u2013320.","DOI":"10.1111\/j.1467-9868.2005.00503.x"},{"key":"16","doi-asserted-by":"publisher","unstructured":"<small>B\u00fchlmann, P.<\/small> and <small>van de Geer, S.<\/small> (2011). <i>Statistics for High-Dimensional Data<\/i>: <i>Methods, Theory and Applications<\/i>. <i>Springer Series in Statistics<\/i>. Springer, Heidelberg.","DOI":"10.1007\/978-3-642-20192-9"},{"key":"71","doi-asserted-by":"publisher","unstructured":"<small>Meinshausen, N.<\/small> and <small>B\u00fchlmann, P.<\/small> (2006). High-dimensional graphs and variable selection with the lasso. <i>Ann. Statist.<\/i> <b>34<\/b> 1436\u20131462.","DOI":"10.1214\/009053606000000281"},{"key":"101","doi-asserted-by":"publisher","unstructured":"<small>Zhang, C.-H.<\/small> (2010). Nearly unbiased variable selection under minimax concave penalty. <i>Ann. Statist.<\/i> <b>38<\/b> 894\u2013942.","DOI":"10.1214\/09-AOS729"},{"key":"104","unstructured":"<small>Zhao, P.<\/small> and <small>Yu, B.<\/small> (2006). On model selection consistency of Lasso. <i>J. Mach. Learn. Res.<\/i> <b>7<\/b> 2541\u20132563."},{"key":"34","doi-asserted-by":"publisher","unstructured":"<small>Donoho, D. L.<\/small> (2006). Compressed sensing. <i>IEEE Trans. Inf. Theory<\/i> <b>52<\/b> 1289\u20131306.","DOI":"10.1109\/TIT.2006.871582"},{"key":"66","unstructured":"<small>Loh, P.-L.<\/small> and <small>Wainwright, M. J.<\/small> (2015). Regularized <i>M<\/i>-estimators with nonconvexity: Statistical and algorithmic theory for local optima. <i>J. Mach. Learn. Res.<\/i> <b>16<\/b> 559\u2013616."},{"key":"53","doi-asserted-by":"crossref","unstructured":"<small>Huber, P. J.<\/small> (1973). Robust regression: Asymptotics, conjectures and Monte Carlo. <i>Ann. Statist.<\/i> <b>1<\/b> 799\u2013821.","DOI":"10.1214\/aos\/1176342503"},{"key":"27","doi-asserted-by":"publisher","unstructured":"<small>Chen, Y.<\/small>, <small>Chi, Y.<\/small>, <small>Fan, J.<\/small> and <small>Ma, C.<\/small> (2019a). Gradient descent with random initialization: Fast global convergence for nonconvex phase retrieval. <i>Math. Program.<\/i> <b>176<\/b> 5\u201337.","DOI":"10.1007\/s10107-019-01363-6"},{"key":"33","doi-asserted-by":"publisher","unstructured":"<small>Donoho, D.<\/small> and <small>Montanari, A.<\/small> (2016). High dimensional robust M-estimation: Asymptotic variance via approximate message passing. <i>Probab. Theory Related Fields<\/i> <b>166<\/b> 935\u2013969.","DOI":"10.1007\/s00440-015-0675-z"},{"key":"42","doi-asserted-by":"crossref","unstructured":"<small>El Karoui, N.<\/small>, <small>Bean, D.<\/small>, <small>Bickel, P. J.<\/small>, <small>Lim, C.<\/small> and <small>Yu, B.<\/small> (2013). On robust regression with high-dimensional predictors. <i>Proc. Natl. Acad. Sci. USA<\/i> <b>110<\/b> 14557\u201314562.","DOI":"10.1073\/pnas.1307842110"},{"key":"67","doi-asserted-by":"publisher","unstructured":"<small>Ma, C.<\/small>, <small>Wang, K.<\/small>, <small>Chi, Y.<\/small> and <small>Chen, Y.<\/small> (2020). Implicit regularization in nonconvex statistical estimation: Gradient descent converges linearly for phase retrieval, matrix completion, and blind deconvolution. <i>Found. Comput. Math.<\/i> <b>20<\/b> 451\u2013632.","DOI":"10.1007\/s10208-019-09429-9"},{"key":"100","doi-asserted-by":"publisher","unstructured":"<small>Yuan, M.<\/small> and <small>Lin, Y.<\/small> (2006). Model selection and estimation in regression with grouped variables. <i>J. R. Stat. Soc. Ser. B. Stat. Methodol.<\/i> <b>68<\/b> 49\u201367.","DOI":"10.1111\/j.1467-9868.2005.00532.x"},{"key":"51","unstructured":"<small>Hastie, T.<\/small>, <small>Tibshirani, R.<\/small> and <small>Wainwright, M.<\/small> (2015). <i>Statistical Learning with Sparsity<\/i>: <i>The Lasso and Generalizations<\/i>. <i>Monographs on Statistics and Applied Probability<\/i> <b>143<\/b>. CRC Press, Boca Raton, FL."},{"key":"81","doi-asserted-by":"publisher","unstructured":"<small>Ren, Z.<\/small>, <small>Sun, T.<\/small>, <small>Zhang, C.-H.<\/small> and <small>Zhou, H. H.<\/small> (2015). Asymptotic normality and optimalities in estimation of large Gaussian graphical models. <i>Ann. Statist.<\/i> <b>43<\/b> 991\u20131026.","DOI":"10.1214\/14-AOS1286"},{"key":"92","doi-asserted-by":"publisher","unstructured":"<small>van de Geer, S.<\/small>, <small>B\u00fchlmann, P.<\/small>, <small>Ritov, Y.<\/small> and <small>Dezeure, R.<\/small> (2014). On asymptotically optimal confidence regions and tests for high-dimensional models. <i>Ann. Statist.<\/i> <b>42<\/b> 1166\u20131202.","DOI":"10.1214\/14-AOS1221"},{"key":"102","doi-asserted-by":"publisher","unstructured":"<small>Zhang, C.-H.<\/small> and <small>Zhang, S. S.<\/small> (2014). Confidence intervals for low dimensional parameters in high dimensional linear models. <i>J. R. Stat. Soc. Ser. B. Stat. Methodol.<\/i> <b>76<\/b> 217\u2013242.","DOI":"10.1111\/rssb.12026"},{"key":"25","doi-asserted-by":"publisher","unstructured":"<small>Chen, S. S.<\/small>, <small>Donoho, D. L.<\/small> and <small>Saunders, M. A.<\/small> (2001). Atomic decomposition by basis pursuit. <i>SIAM Rev.<\/i> <b>43<\/b> 129\u2013159.","DOI":"10.1137\/S003614450037906X"},{"key":"65","doi-asserted-by":"publisher","unstructured":"<small>Loh, P.-L.<\/small> (2017). Statistical consistency and asymptotic normality for high-dimensional robust <i>M<\/i>-estimators. <i>Ann. Statist.<\/i> <b>45<\/b> 866\u2013896.","DOI":"10.1214\/16-AOS1471"},{"key":"87","doi-asserted-by":"publisher","unstructured":"<small>Sun, Q.<\/small>, <small>Zhou, W.-X.<\/small> and <small>Fan, J.<\/small> (2020). Adaptive Huber regression. <i>J. Amer. Statist. Assoc.<\/i> <b>115<\/b> 254\u2013265.","DOI":"10.1080\/01621459.2018.1543124"},{"key":"55","doi-asserted-by":"publisher","unstructured":"<small>Javanmard, A.<\/small> and <small>Montanari, A.<\/small> (2014). Hypothesis testing in high-dimensional regression under the Gaussian random design model: Asymptotic theory. <i>IEEE Trans. Inf. Theory<\/i> <b>60<\/b> 6522\u20136554.","DOI":"10.1109\/TIT.2014.2343629"},{"key":"35","doi-asserted-by":"publisher","unstructured":"<small>DONOHO, D. L.<\/small> and <small>HUO, X.<\/small> (2001). Uncertainty principles and ideal atomic decomposition. <i>IEEE Trans. Inf. Theory<\/i> <b>47<\/b> 2845\u20132862.","DOI":"10.1109\/18.959265"},{"key":"47","doi-asserted-by":"crossref","unstructured":"<small>FENG, O. Y.<\/small>, <small>VENKATARAMANAN, R.<\/small>, <small>RUSH, C.<\/small> and <small>SAMWORTH, R. J.<\/small> (2022). A unifying tutorial on approximate message passing. <i>Found. Trends Mach. Learn.<\/i> <b>15<\/b> 335\u2013536.","DOI":"10.1561\/2200000092"},{"key":"61","unstructured":"<small>LI, G.<\/small> and <small>WEI, Y.<\/small> (2022). A non-asymptotic framework for approximate message passing in spiked models. Preprint. Available at arXiv:<a href=\"https:\/\/arxiv.org\/abs\/2208.03313\">2208.03313<\/a>."},{"key":"74","unstructured":"<small>MONDELLI, M.<\/small> and <small>VENKATARAMANAN, R.<\/small> (2021). PCA initialization for approximate message passing in rotationally invariant models. <i>Adv. Neural Inf. Process. Syst.<\/i> <b>34<\/b> 29616\u201329629."},{"key":"79","doi-asserted-by":"crossref","unstructured":"<small>RANGAN, S.<\/small> (2011). Generalized approximate message passing for estimation with random linear mixing. In 2011 <i>IEEE International Symposium on Information Theory Proceedings<\/i> 2168\u20132172. IEEE.","DOI":"10.1109\/ISIT.2011.6033942"},{"key":"99","doi-asserted-by":"publisher","unstructured":"<small>YAN, Y.<\/small>, <small>CHEN, Y.<\/small> and <small>FAN, J.<\/small> (2024). Inference for heteroskedastic PCA with missing data. <i>Ann. Statist.<\/i> <b>52<\/b> 729\u2013756.","DOI":"10.1214\/24-aos2366"},{"key":"78","doi-asserted-by":"publisher","unstructured":"<small>NGUYEN, N. H.<\/small> and <small>TRAN, T. D.<\/small> (2013). Robust Lasso with missing and grossly corrupted observations. <i>IEEE Trans. Inf. Theory<\/i> <b>59<\/b> 2036\u20132058.","DOI":"10.1109\/TIT.2012.2232347"},{"key":"91","doi-asserted-by":"crossref","unstructured":"<small>TIBSHIRANI, R.<\/small> (1996). Regression shrinkage and selection via the lasso. <i>J. Roy. Statist. Soc. Ser. B, Methodol.<\/i> <b>58<\/b> 267\u2013288.","DOI":"10.1111\/j.2517-6161.1996.tb02080.x"},{"key":"3","doi-asserted-by":"publisher","unstructured":"<small>BAO, Z.<\/small>, <small>HAN, Q.<\/small> and <small>XU, X.<\/small> (2025). A leave-one-out approach to approximate message passing. <i>Ann. Appl. Probab.<\/i> <b>35<\/b> 2716\u20132766.","DOI":"10.1214\/25-AAP2186"},{"key":"1","doi-asserted-by":"publisher","unstructured":"<small>ADOMAITYTE, U.<\/small>, <small>DEFILIPPIS, L.<\/small>, <small>LOUREIRO, B.<\/small> and <small>SICURO, G.<\/small> (2024). High-dimensional robust regression under heavy-tailed data: Asymptotics and universality. <i>J. Stat. Mech. Theory Exp.<\/i> <b>2024<\/b> Paper No. 114002, 36 pp.","DOI":"10.1088\/1742-5468\/ad65e6"},{"key":"8","unstructured":"<small>BELLEC, P. C.<\/small> and <small>KORIYAMA, T.<\/small> (2025). Error estimation and adaptive tuning for unregularized robust M-estimator. <i>J. Mach. Learn. Res.<\/i> <b>26<\/b> Paper No. [16], 40 pp."},{"key":"13","doi-asserted-by":"publisher","unstructured":"<small>BOGDAN, M.<\/small>, <small>VAN DEN BERG, E.<\/small>, <small>SABATTI, C.<\/small>, <small>SU, W.<\/small> and <small>CANDES, E. J.<\/small> (2015). SLOPE\u2014adaptive variable selection via convex optimization. <i>Ann. Appl. Stat.<\/i> <b>9<\/b> 1103\u20131140.","DOI":"10.1214\/15-AOAS842"},{"key":"14","unstructured":"<small>BOLTHAUSEN, E.<\/small> (2009). On the high-temperature phase of the Sherrington\u2013Kirkpatrick model. In <i>Seminar at EURANDOM, Eindhoven<\/i>."},{"key":"19","doi-asserted-by":"crossref","unstructured":"<small>CANDES, E.<\/small> and <small>TAO, T.<\/small> (2007). The Dantzig selector: Statistical estimation when p is much larger than n.","DOI":"10.1214\/009053606000001523"},{"key":"20","doi-asserted-by":"publisher","unstructured":"<small>CANDES, E. J.<\/small>, <small>ROMBERG, J. K.<\/small> and <small>TAO, T.<\/small> (2006). Stable signal recovery from incomplete and inaccurate measurements. <i>Comm. Pure Appl. Math.<\/i> <b>59<\/b> 1207\u20131223.","DOI":"10.1002\/cpa.20124"},{"key":"21","unstructured":"<small>CELENTANO, M.<\/small>, <small>FAN, Z.<\/small>, <small>LIN, L.<\/small> and <small>MEI, S.<\/small> (2023). Mean-field variational inference with the TAP free energy: Geometric and statistical properties in linear models. Preprint. Available at arXiv:<a href=\"https:\/\/arxiv.org\/abs\/2311.08442\">2311.08442<\/a>."},{"key":"23","unstructured":"<small>CELENTANO, M.<\/small> and <small>MONTANARI, A.<\/small> (2021). Cad: Debiasing the lasso with inaccurate covariate model. Preprint. Available at arXiv:<a href=\"https:\/\/arxiv.org\/abs\/2107.14172\">2107.14172<\/a>."},{"key":"29","unstructured":"<small>DALALYAN, A.<\/small> and <small>CHEN, Y.<\/small> (2012). Fused sparsity and robust estimation for linear models with unknown variance. <i>Adv. Neural Inf. Process. Syst.<\/i> <b>25<\/b>."},{"key":"30","unstructured":"<small>DALALYAN, A.<\/small> and <small>THOMPSON, P.<\/small> (2019). Outlier-robust estimation of a sparse linear model using <math xmlns=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" overflow=\"scroll\" id=\"eq_3\"><msub><mrow><mi>\u2113<\/mi><\/mrow><mrow><mn>1<\/mn><\/mrow><\/msub><\/math>-penalized Huber\u2019s <i>m<\/i>-estimator. <i>Adv. Neural Inf. Process. Syst.<\/i> <b>32<\/b>."},{"key":"38","unstructured":"<small>DONOHO, D. L.<\/small> and <small>MONTANARI, A.<\/small> (2015). Variance breakdown of Huber (m)-estimators. <math xmlns=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" overflow=\"scroll\" id=\"eq_4\"><mi mathvariant=\"italic\">n<\/mi><mo stretchy=\"false\">\/<\/mo><mi mathvariant=\"italic\">p<\/mi><mo stretchy=\"false\">\u2192<\/mo><mi mathvariant=\"italic\">m<\/mi><mspace width=\"2.5pt\" \/><mtext>in<\/mtext><mo fence=\"true\" stretchy=\"false\">(<\/mo><mn>1<\/mn><mo>,<\/mo><mi>\u221e<\/mi><mo fence=\"true\" stretchy=\"false\">)<\/mo><\/math>. Preprint. Available at arXiv:<a href=\"https:\/\/arxiv.org\/abs\/1503.02106\">1503.02106<\/a>."},{"key":"43","unstructured":"<small>FAN, J.<\/small>, <small>LI, Q.<\/small> and <small>WANG, Y.<\/small> (2014). Robust estimation of high-dimensional mean regression. Preprint. Available at arXiv:<a href=\"https:\/\/arxiv.org\/abs\/1410.2150\">1410.2150<\/a>."},{"key":"48","doi-asserted-by":"crossref","unstructured":"<small>FISHER, R. A.<\/small> (1922). On the mathematical foundations of theoretical statistics. <i>Philos. Trans. R. Soc. Lond. Ser. A Math. Phys. Eng. Sci.<\/i> <b>222<\/b> 309\u2013368.","DOI":"10.1098\/rsta.1922.0009"},{"key":"57","doi-asserted-by":"crossref","unstructured":"<small>LASKA, J. N.<\/small>, <small>DAVENPORT, M. A.<\/small> and <small>BARANIUK, R. G.<\/small> (2009). Exact signal recovery from sparsely corrupted measurements through the pursuit of justice. In 2009 <i>Conference Record of the Forty-Third Asilomar Conference on Signals, Systems and Computers<\/i> 1556\u20131560. IEEE.","DOI":"10.1109\/ACSSC.2009.5470141"},{"key":"60","doi-asserted-by":"publisher","unstructured":"<small>LI, G.<\/small>, <small>FAN, W.<\/small> and <small>WEI, Y.<\/small> (2023). Approximate message passing from random initialization with applications to <math xmlns=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" overflow=\"scroll\" id=\"eq_5\"><msub><mrow><mi mathvariant=\"double-struck\">Z<\/mi><\/mrow><mrow><mn>2<\/mn><\/mrow><\/msub><\/math> synchronization. <i>Proc. Natl. Acad. Sci. USA<\/i> <b>120<\/b> Paper No. e2302930120, 7 pp.","DOI":"10.1073\/pnas.2302930120"},{"key":"62","doi-asserted-by":"crossref","unstructured":"<small>LI, G.<\/small> and <small>WEI, Y.<\/small> (2026). Supplement to \u201cA nonasymptotic distributional theory of approximate message passing for sparse and robust regression.\u201d <a href=\"https:\/\/doi.org\/10.1214\/25-AOS2612SUPP\">https:\/\/doi.org\/10.1214\/25-AOS2612SUPP<\/a>","DOI":"10.1214\/25-AOS2612SUPP"},{"key":"64","unstructured":"<small>LI, Y.<\/small> and <small>WEI, Y.<\/small> (2021). Minimum <math xmlns=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" overflow=\"scroll\" id=\"eq_6\"><msub><mrow><mi>\u2113<\/mi><\/mrow><mrow><mn>1<\/mn><\/mrow><\/msub><\/math>-norm interpolators: Precise asymptotics and multiple descent. Preprint. Available at arXiv:<a href=\"https:\/\/arxiv.org\/abs\/2110.09502\">2110.09502<\/a>."},{"key":"77","unstructured":"<small>MONTANARI, A.<\/small> and <small>WU, Y.<\/small> (2023). Posterior sampling from the spiked models via diffusion processes. Preprint. Available at arXiv:<a href=\"https:\/\/arxiv.org\/abs\/2304.11449\">2304.11449<\/a>."},{"key":"82","doi-asserted-by":"publisher","unstructured":"<small>ROUSSEEUW, P. J.<\/small> and <small>LEROY, A. M.<\/small> (2005). <i>Robust Regression and Outlier Detection<\/i>. <i>Wiley Series in Probability and Mathematical Statistics<\/i>: <i>Applied Probability and Statistics<\/i>. Wiley, New York.","DOI":"10.1002\/0471725382"},{"key":"86","doi-asserted-by":"publisher","unstructured":"<small>SU, W.<\/small>, <small>BOGDAN, M.<\/small> and <small>CANDES, E.<\/small> (2017). False discoveries occur early on the Lasso path. <i>Ann. Statist.<\/i> <b>45<\/b> 2133\u20132150.","DOI":"10.1214\/16-AOS1521"},{"key":"88","doi-asserted-by":"publisher","unstructured":"<small>SUR, P.<\/small> and <small>CANDES, E. J.<\/small> (2019). A modern maximum-likelihood theory for high-dimensional logistic regression. <i>Proc. Natl. Acad. Sci. USA<\/i> <b>116<\/b> 14516\u201314525.","DOI":"10.1073\/pnas.1810420116"},{"key":"89","doi-asserted-by":"publisher","unstructured":"<small>SUR, P.<\/small>, <small>CHEN, Y.<\/small> and <small>CANDES, E. J.<\/small> (2019). The likelihood ratio test in high-dimensional logistic regression is asymptotically a <i>rescaled<\/i> chi-square. <i>Probab. Theory Related Fields<\/i> <b>175<\/b> 487\u2013558.","DOI":"10.1007\/s00440-018-00896-9"},{"key":"94","unstructured":"<small>VENKATARAMANAN, R.<\/small>, <small>K\u00d6GLER, K.<\/small> and <small>MONDELLI, M.<\/small> (2021). Estimation in rotationally invariant generalized linear models via approximate message passing. Preprint. Available at arXiv:<a href=\"https:\/\/arxiv.org\/abs\/2112.04330\">2112.04330<\/a>."},{"key":"97","unstructured":"<small>WU, Y.<\/small> and <small>ZHOU, K.<\/small> (2024). Sharp analysis of power iteration for tensor PCA. <i>J. Mach. Learn. Res.<\/i> <b>25<\/b> Paper No. [195], 42 pp."},{"key":"103","doi-asserted-by":"publisher","unstructured":"<small>ZHANG, Y.<\/small>, <small>JI, H. C.<\/small>, <small>VENKATARAMANAN, R.<\/small> and <small>MONDELLI, M.<\/small> (2025). Spectral estimators for structured generalized linear models via approximate message passing. <i>Math. Stat. Learn.<\/i> <b>8<\/b> 193\u2013304.","DOI":"10.4171\/msl\/52"},{"key":"50","doi-asserted-by":"publisher","unstructured":"<small>HAN, Q.<\/small> and <small>SHEN, Y.<\/small> (2023). Universality of regularized regression estimators in high dimensions. <i>Ann. Statist.<\/i> <b>51<\/b> 1799\u20131823.","DOI":"10.1214\/23-aos2309"},{"key":"22","doi-asserted-by":"publisher","unstructured":"<small>CELENTANO, M.<\/small>, <small>FAN, Z.<\/small> and <small>MEI, S.<\/small> (2023). Local convexity of the TAP free energy and AMP convergence for <math xmlns=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" overflow=\"scroll\" id=\"eq_2\"><msub><mrow><mi mathvariant=\"double-struck\">Z<\/mi><\/mrow><mrow><mn>2<\/mn><\/mrow><\/msub><\/math>-synchronization. <i>Ann. Statist.<\/i> <b>51<\/b> 519\u2013546.","DOI":"10.1214\/23-aos2257"},{"key":"18","doi-asserted-by":"crossref","unstructured":"<small>CAI, C.<\/small>, <small>POOR, H. V.<\/small> and <small>CHEN, Y.<\/small> (2023). Uncertainty quantification for nonconvex tensor completion: Confidence intervals, heteroscedasticity and optimality. <i>IEEE Trans. Inf. Theory<\/i> <b>69<\/b> 407\u2013452.","DOI":"10.1109\/TIT.2022.3205781"},{"key":"24","doi-asserted-by":"publisher","unstructured":"<small>CELENTANO, M.<\/small>, <small>MONTANARI, A.<\/small> and <small>WEI, Y.<\/small> (2023). The Lasso with general Gaussian designs with applications to hypothesis testing. <i>Ann. Statist.<\/i> <b>51<\/b> 2194\u20132220.","DOI":"10.1214\/23-aos2327"},{"key":"12","doi-asserted-by":"crossref","unstructured":"<small>BICKEL, P. J.<\/small> (1975). One-step Huber estimates in the linear model. <i>J. Amer. Statist. Assoc.<\/i> <b>70<\/b> 428\u2013434.","DOI":"10.1080\/01621459.1975.10479884"},{"key":"9","doi-asserted-by":"publisher","unstructured":"<small>BELLEC, P. C.<\/small>, <small>SHEN, Y.<\/small> and <small>ZHANG, C.-H.<\/small> (2022). Asymptotic normality of robust <i>M<\/i>-estimators with convex penalty. <i>Electron. J. Stat.<\/i> <b>16<\/b> 5591\u20135622.","DOI":"10.1214\/22-ejs2065"},{"key":"40","unstructured":"<small>EL KAROUI, N.<\/small> (2013). Asymptotic behavior of unregularized and ridge-regularized high-dimensional robust regression estimators: Rigorous results. Preprint. Available at arXiv:<a href=\"https:\/\/arxiv.org\/abs\/1311.2445\">1311.2445<\/a>."},{"key":"17","doi-asserted-by":"publisher","unstructured":"<small>CADEMARTORI, C.<\/small> and <small>RUSH, C.<\/small> (2024). A non-asymptotic analysis of generalized vector approximate message passing algorithms with rotationally invariant designs. <i>IEEE Trans. Inf. Theory<\/i> <b>70<\/b> 5811\u20135856.","DOI":"10.1109\/tit.2024.3396472"},{"key":"32","doi-asserted-by":"crossref","unstructured":"<small>DESHPANDE, Y.<\/small> and <small>MONTANARI, A.<\/small> (2014). Information-theoretically optimal sparse PCA. In 2014 <i>IEEE International Symposium on Information Theory<\/i> 2197\u20132201. IEEE.","DOI":"10.1109\/ISIT.2014.6875223"},{"key":"39","doi-asserted-by":"publisher","unstructured":"<small>DUDEJA, R.<\/small>, <small>LU, Y. M.<\/small> and <small>SEN, S.<\/small> (2023). Universality of approximate message passing with semirandom matrices. <i>Ann. Probab.<\/i> <b>51<\/b> 1616\u20131683.","DOI":"10.1214\/23-aop1628"},{"key":"75","doi-asserted-by":"publisher","unstructured":"<small>MONDELLI, M.<\/small> and <small>VENKATARAMANAN, R.<\/small> (2022). Approximate message passing with spectral initialization for generalized linear models. <i>J. Stat. Mech. Theory Exp.<\/i> <b>2022<\/b> Paper No. 114003, 41 pp.","DOI":"10.1088\/1742-5468\/ac9828"},{"key":"96","doi-asserted-by":"publisher","unstructured":"<small>WANG, T.<\/small>, <small>ZHONG, X.<\/small> and <small>FAN, Z.<\/small> (2024). Universality of approximate message passing algorithms and tensor networks. <i>Ann. Appl. Probab.<\/i> <b>34<\/b> 3943\u20133994.","DOI":"10.1214\/24-aap2056"},{"key":"105","doi-asserted-by":"publisher","unstructured":"<small>ZHONG, X.<\/small>, <small>WANG, T.<\/small> and <small>FAN, Z.<\/small> (2024). Approximate message passing for orthogonally invariant ensembles: Multivariate non-linearities and spectral initialization. <i>Inf. Inference<\/i> <b>13<\/b> Paper No. iaae024, 22 pp.","DOI":"10.1093\/imaiai\/iaae024"},{"key":"68","doi-asserted-by":"publisher","unstructured":"<small>MA, Z.<\/small> and <small>NANDY, S.<\/small> (2023). Community detection with contextual multilayer networks. <i>IEEE Trans. Inf. Theory<\/i> <b>69<\/b> 3203\u20133239.","DOI":"10.1109\/tit.2023.3238352"},{"key":"63","doi-asserted-by":"publisher","unstructured":"<small>LI, Y.<\/small>, <small>FAN, Z.<\/small>, <small>SEN, S.<\/small> and <small>WU, Y.<\/small> (2024). Random linear estimation with rotationally-invariant designs: Asymptotics at high temperature. <i>IEEE Trans. Inf. Theory<\/i> <b>70<\/b> 2118\u20132153.","DOI":"10.1109\/tit.2023.3321575"}],"container-title":["The Annals of Statistics"],"original-title":[],"deposited":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T21:12:08Z","timestamp":1791321128000},"score":1,"resource":{"primary":{"URL":"https:\/\/projecteuclid.org\/journals\/annals-of-statistics\/volume-54\/issue-4\/A-nonasymptotic-distributional-theory-of-approximate-message-passing-for-sparse\/10.1214\/25-AOS2612.full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,1]]},"references-count":106,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,8,1]]}},"URL":"https:\/\/doi.org\/10.1214\/25-aos2612","relation":{},"ISSN":["0090-5364","2168-8966"],"issn-type":[{"value":"0090-5364","type":"print"},{"value":"2168-8966","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,1]]}}}