{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T18:50:54Z","timestamp":1784919054468,"version":"3.55.0"},"reference-count":74,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2023,12,18]],"date-time":"2023-12-18T00:00:00Z","timestamp":1702857600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,18]],"date-time":"2023-12-18T00:00:00Z","timestamp":1702857600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Mach Intell"],"DOI":"10.1038\/s42256-023-00767-6","type":"journal-article","created":{"date-parts":[[2023,12,18]],"date-time":"2023-12-18T17:02:50Z","timestamp":1702918970000},"page":"1497-1507","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":35,"title":["A statistical mechanics framework for Bayesian deep neural networks beyond the infinite-width limit"],"prefix":"10.1038","volume":"5","author":[{"given":"R.","family":"Pacelli","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"S.","family":"Ariosto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2771-7437","authenticated-orcid":false,"given":"M.","family":"Pastore","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"F.","family":"Ginelli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7745-8269","authenticated-orcid":false,"given":"M.","family":"Gherardi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6745-6166","authenticated-orcid":false,"given":"P.","family":"Rotondo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,12,18]]},"reference":[{"key":"767_CR1","unstructured":"Goodfellow, I., Bengio, Y. & Courville, A. Deep Learning (MIT Press, 2016)."},{"key":"767_CR2","doi-asserted-by":"crossref","unstructured":"Engel, A. & Van den Broeck, C. Statistical Mechanics of Learning (Cambridge Univ. Press, 2001).","DOI":"10.1017\/CBO9781139164542"},{"key":"767_CR3","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-36361-y","volume":"14","author":"I Seroussi","year":"2023","unstructured":"Seroussi, I., Naveh, G. & Ringel, Z. Separation of scales and a thermodynamic description of feature learning in some CNNs. Nat. Commun. 14, 908 (2023).","journal-title":"Nat. Commun."},{"key":"767_CR4","doi-asserted-by":"publisher","first-page":"027301","DOI":"10.1103\/PhysRevLett.131.027301","volume":"131","author":"AJ Wakhloo","year":"2023","unstructured":"Wakhloo, A. J., Sussman, T. J. & Chung, S. Linear classification of neural manifolds with correlated variability. Phys. Rev. Lett. 131, 027301 (2023).","journal-title":"Phys. Rev. Lett."},{"key":"767_CR5","first-page":"031059","volume":"11","author":"Q Li","year":"2021","unstructured":"Li, Q. & Sompolinsky, H. Statistical mechanics of deep linear neural networks: the backpropagating kernel renormalization. Phys. Rev. X 11, 031059 (2021).","journal-title":"Phys. Rev. X"},{"key":"767_CR6","doi-asserted-by":"publisher","first-page":"014116","DOI":"10.1103\/PhysRevE.106.014116","volume":"106","author":"C Baldassi","year":"2022","unstructured":"Baldassi, C. et al. Learning through atypical phase transitions in overparameterized neural networks. Phys. Rev. E 106, 014116 (2022).","journal-title":"Phys. Rev. E"},{"key":"767_CR7","doi-asserted-by":"publisher","first-page":"2914","DOI":"10.1038\/s41467-021-23103-1","volume":"12","author":"A Canatar","year":"2021","unstructured":"Canatar, A., Bordelon, B. & Pehlevan, C. Spectral bias and task-model alignment explain generalization in kernel regression and infinitely wide neural networks. Nat. Commun. 12, 2914 (2021).","journal-title":"Nat. Commun."},{"key":"767_CR8","doi-asserted-by":"publisher","first-page":"168301","DOI":"10.1103\/PhysRevLett.125.168301","volume":"125","author":"A Mozeika","year":"2020","unstructured":"Mozeika, A., Li, B. & Saad, D. Space of functions computed by deep-layered machines. Phys. Rev. Lett. 125, 168301 (2020).","journal-title":"Phys. Rev. Lett."},{"key":"767_CR9","first-page":"041044","volume":"10","author":"S Goldt","year":"2020","unstructured":"Goldt, S., M\u00e9zard, M., Krzakala, F. & Zdeborov\u00e1, L. Modeling the influence of data structure on learning in neural networks: the hidden manifold model. Phys. Rev. X 10, 041044 (2020).","journal-title":"Phys. Rev. X"},{"key":"767_CR10","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1146\/annurev-conmatphys-031119-050745","volume":"11","author":"Y Bahri","year":"2020","unstructured":"Bahri, Y. et al. Statistical mechanics of deep learning. Ann. Rev. Condensed Matter Phys. 11, 501\u2013528 (2020).","journal-title":"Ann. Rev. Condensed Matter Phys."},{"key":"767_CR11","doi-asserted-by":"publisher","first-page":"248301","DOI":"10.1103\/PhysRevLett.120.248301","volume":"120","author":"B Li","year":"2018","unstructured":"Li, B. & Saad, D. Exploring the function space of deep-learning machines. Phys. Rev. Lett. 120, 248301 (2018).","journal-title":"Phys. Rev. Lett."},{"key":"767_CR12","doi-asserted-by":"crossref","unstructured":"Neal, R. M. in Bayesian Learning for Neural Networks 29\u201353 (Springer, 1996).","DOI":"10.1007\/978-1-4612-0745-0_2"},{"key":"767_CR13","unstructured":"Williams, C. Computing with infinite networks. In Proc. 9th International Conference on Neural Information Processing Systems (eds Jordan, M. I. & Petsche, T.) 295\u2013301 (MIT Press, 1996)."},{"key":"767_CR14","unstructured":"de G. Matthews, A. G., Hron, J., Rowland, M., Turner, R. E. & Ghahramani, Z. Gaussian process behaviour in wide deep neural networks. In International Conference on Learning Representations (ICLR, 2018)."},{"key":"767_CR15","unstructured":"Lee, J. et al. Deep neural networks as Gaussian processes. In International Conference on Learning Representations (ICLR, 2018)."},{"key":"767_CR16","unstructured":"Garriga-Alonso, A., Rasmussen, C. E. & Aitchison, L. Deep convolutional networks as shallow Gaussian processes. In International Conference on Learning Representations (ICLR, 2019)."},{"key":"767_CR17","unstructured":"Novak, R. et al. Bayesian deep convolutional networks with many channels are Gaussian processes. In International Conference on Learning Representations (ICLR, 2019)."},{"key":"767_CR18","unstructured":"Jacot, A., Gabriel, F. & Hongler, C. Neural tangent kernel: convergence and generalization in neural networks. In Proc. 32nd International Conference on Neural Information Processing Systems (ed. Bengio, S. et al.) 8580\u20138589 (Curran Associates, 2018)."},{"key":"767_CR19","unstructured":"Chizat, L., Oyallon, E. & Bach, F. On lazy training in differentiable programming. In Proc. 33rd International Conference on Neural Information Processing Systems (ed. Wallach, H. et al.) 2937\u20132947 (Curran Associates, 2019)."},{"key":"767_CR20","unstructured":"Lee, J. et al. Wide neural networks of any depth evolve as linear models under gradient descent. In Proc. 33rd International Conference on Neural Information Processing Systems (eds Wallach, H. et al.) 8572\u20138583 (Curran Associates, 2019)."},{"key":"767_CR21","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/BF00994018","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes, C. & Vapnik, V. Support-vector networks. Mach. Learn. 20, 273\u2013297 (1995).","journal-title":"Mach. Learn."},{"key":"767_CR22","unstructured":"Bordelon, B., Canatar, A. & Pehlevan, C. Spectrum dependent learning curves in kernel regression and wide neural networks. In Proc. 37th International Conference on Machine Learning (eds Daum\u00e9, H. III & Singh, A.) 1024\u20131034 (PMLR, 2020)."},{"key":"767_CR23","doi-asserted-by":"publisher","first-page":"2975","DOI":"10.1103\/PhysRevLett.82.2975","volume":"82","author":"R Dietrich","year":"1999","unstructured":"Dietrich, R., Opper, M. & Sompolinsky, H. Statistical mechanics of support vector networks. Phys. Rev. Lett. 82, 2975\u20132978 (1999).","journal-title":"Phys. Rev. Lett."},{"key":"767_CR24","unstructured":"Seleznova, M. & Kutyniok, G. Neural tangent kernel beyond the infinite-width limit: effects of depth and initialization. Preprint at https:\/\/arxiv.org\/abs\/2202.00553 (2022)."},{"key":"767_CR25","unstructured":"Vyas, N., Bansal, Y. & Preetum, N. Limitations of the NTK for understanding generalization in deep learning. Preprint at https:\/\/arxiv.org\/abs\/2206.10012 (2022)."},{"key":"767_CR26","unstructured":"Antognini, J. M. Finite size corrections for neural network gaussian processes Preprint at https:\/\/arxiv.org\/abs\/1908.10030 (2019)."},{"key":"767_CR27","unstructured":"Yaida, S. Non-Gaussian processes and neural networks at finite widths. In Proc. 1st Mathematical and Scientific Machine Learning Conference (eds Lu, J. & Ward, R.) 165\u2013192 (PMLR, 2020)."},{"key":"767_CR28","unstructured":"Hanin, B. Random fully connected neural networks as perturbatively solvable hierarchies. Preprint at https:\/\/arxiv.org\/abs\/2204.01058 (2023)."},{"key":"767_CR29","unstructured":"Zavatone-Veth, J. & Pehlevan, C. Exact marginal prior distributions of finite bayesian neural networks. In Advances in Neural Information Processing Systems (eds Vaughan, J. et al.) 3364\u20133375 (Curran Associates, 2021)."},{"key":"767_CR30","doi-asserted-by":"crossref","unstructured":"Bengio, Y. & Delalleau, O. in Algorithmic Learning Theory (eds Kivinen, J. et al.) 18\u201336 (Springer, 2011).","DOI":"10.1007\/978-3-642-24412-4_3"},{"key":"767_CR31","first-page":"2285","volume":"20","author":"PL Bartlett","year":"2019","unstructured":"Bartlett, P. L., Harvey, N., Liaw, C. & Mehrabian, A. Nearly-tight VC-dimension and pseudodimension bounds for piecewise linear neural networks. J. Mach. Learn. Res. 20, 2285\u20132301 (2019).","journal-title":"J. Mach. Learn. Res."},{"key":"767_CR32","doi-asserted-by":"publisher","first-page":"023169","DOI":"10.1103\/PhysRevResearch.2.023169","volume":"2","author":"P Rotondo","year":"2020","unstructured":"Rotondo, P., Lagomarsino, M. C. & Gherardi, M. Counting the learnable functions of geometrically structured data. Phys. Rev. Res. 2, 023169 (2020).","journal-title":"Phys. Rev. Res."},{"key":"767_CR33","doi-asserted-by":"publisher","first-page":"120601","DOI":"10.1103\/PhysRevLett.125.120601","volume":"125","author":"P Rotondo","year":"2020","unstructured":"Rotondo, P., Pastore, M. & Gherardi, M. Beyond the storage capacity: data-driven satisfiability transition. Phys. Rev. Lett. 125, 120601 (2020).","journal-title":"Phys. Rev. Lett."},{"key":"767_CR34","doi-asserted-by":"publisher","first-page":"032119","DOI":"10.1103\/PhysRevE.102.032119","volume":"102","author":"M Pastore","year":"2020","unstructured":"Pastore, M., Rotondo, P., Erba, V. & Gherardi, M. Statistical learning theory of structured data. Phys. Rev. E 102, 032119 (2020).","journal-title":"Phys. Rev. E"},{"key":"767_CR35","doi-asserted-by":"crossref","unstructured":"Gherardi, M. Solvable model for the linear separability of structured data. Entropy 23, 305 (2021).","DOI":"10.3390\/e23030305"},{"key":"767_CR36","doi-asserted-by":"publisher","first-page":"113301","DOI":"10.1088\/1742-5468\/ac312b","volume":"2021","author":"M Pastore","year":"2021","unstructured":"Pastore, M. Critical properties of the SAT\/UNSAT transitions in the classification problem of structured data. J. Stat. Mech. 2021, 113301 (2021).","journal-title":"J. Stat. Mech."},{"key":"767_CR37","doi-asserted-by":"publisher","first-page":"305001","DOI":"10.1088\/1751-8121\/ac79e5","volume":"55","author":"F Aguirre-L\u00f3pez","year":"2022","unstructured":"Aguirre-L\u00f3pez, F., Pastore, M. & Franz, S. Satisfiability transition in asymmetric neural networks. J. Phys. A 55, 305001 (2022).","journal-title":"J. Phys. A"},{"key":"767_CR38","unstructured":"Saxe, A. M., McClelland, J. L. & Ganguli, S. Exact solutions to the nonlinear dynamics of learning in deep linear neural networks. In Proc. 2nd International Conference on Learning Representations (eds. Bengio, Y. & LeCun, Y.) (ICLR, 2014)."},{"key":"767_CR39","doi-asserted-by":"publisher","first-page":"11537","DOI":"10.1073\/pnas.1820226116","volume":"116","author":"AM Saxe","year":"2019","unstructured":"Saxe, A. M., McClelland, J. L. & Ganguli, S. A mathematical theory of semantic development in deep neural networks. Proc. Natl Acad. Sci. USA 116, 11537\u201311546 (2019).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"767_CR40","unstructured":"Zavatone-Veth, J., Canatar, A., Ruben, B. & Pehlevan, C. Asymptotics of representation learning in finite Bayesian neural networks. In Advances in Neural Information Processing Systems (eds Vaughan, J. W. et al.) 24765\u201324777 (Curran Associates, 2021)."},{"key":"767_CR41","unstructured":"Naveh, G. & Ringel, Z. A self consistent theory of gaussian processes captures feature learning effects in finite CNNs. In Advances in Neural Information Processing Systems (eds Vaughan, J. W. et al.) 21352\u201321364 (Curran Associates, 2021)."},{"key":"767_CR42","doi-asserted-by":"publisher","first-page":"064118","DOI":"10.1103\/PhysRevE.105.064118","volume":"105","author":"JA Zavatone-Veth","year":"2022","unstructured":"Zavatone-Veth, J. A., Tong, W. L. & Pehlevan, C. Contrasting random and learned features in deep Bayesian linear regression. Phys. Rev. E 105, 064118 (2022).","journal-title":"Phys. Rev. E"},{"key":"767_CR43","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1016\/j.jmva.2012.08.002","volume":"114","author":"J-M Bardet","year":"2013","unstructured":"Bardet, J.-M. & Surgailis, D. Moment bounds and central limit theorems for Gaussian subordinated arrays. J. Multivariate Anal. 114, 457\u2013473 (2013).","journal-title":"J. Multivariate Anal."},{"key":"767_CR44","doi-asserted-by":"publisher","first-page":"793","DOI":"10.1016\/j.spa.2010.12.006","volume":"121","author":"I Nourdin","year":"2011","unstructured":"Nourdin, I., Peccati, G. & Podolskij, M. Quantitative Breuer\u2013Major theorems. Stochastic Process. Appl. 121, 793\u2013812 (2011).","journal-title":"Stochastic Process. Appl."},{"key":"767_CR45","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1016\/0047-259X(83)90019-2","volume":"13","author":"P Breuer","year":"1983","unstructured":"Breuer, P. & Major, P. Central limit theorems for non-linear functionals of Gaussian fields. J. Multivariate Anal. 13, 425\u2013441 (1983).","journal-title":"J. Multivariate Anal."},{"key":"767_CR46","unstructured":"Gerace, F., Loureiro, B., Krzakala, F., Mezard, M. & Zdeborova, L. Generalisation error in learning with random features and the hidden manifold model. In Proc. 37th International Conference on Machine Learning (eds Daum\u00e9, H. III & Singh, A.) 3452\u20133462 (PMLR, 2020)."},{"key":"767_CR47","doi-asserted-by":"publisher","unstructured":"Loureiro, B. et al. Learning curves of generic features maps for realistic datasets with a teacher-student model. J. Stat. Mech. https:\/\/doi.org\/10.1088\/1742-5468\/ac9825 (2021).","DOI":"10.1088\/1742-5468\/ac9825"},{"key":"767_CR48","unstructured":"Goldt, S. et al. The gaussian equivalence of generative models for learning with shallow neural networks. In Proc. 2nd Mathematical and Scientific Machine Learning Conference (eds. Bruna, J. et al.) 426\u2013471 (PMLR, 2022)."},{"key":"767_CR49","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1214\/17-AOS1549","volume":"46","author":"E Dobriban","year":"2018","unstructured":"Dobriban, E. & Wager, S. High-dimensional asymptotics of prediction: ridge regression and classification. Ann. Stat. 46, 247\u2013279 (2018).","journal-title":"Ann. Stat."},{"key":"767_CR50","doi-asserted-by":"crossref","unstructured":"Mei, S. & Montanari, A. The generalization error of random features regression: precise asymptotics and the double descent curve. Commun. Pure Appl. Math. 75, 667\u2013766 (2019).","DOI":"10.1002\/cpa.22008"},{"key":"767_CR51","doi-asserted-by":"publisher","first-page":"1029 \u2013 1054","DOI":"10.1214\/20-AOS1990","volume":"49","author":"B Ghorbani","year":"2021","unstructured":"Ghorbani, B., Mei, S., Misiakiewicz, T. & Montanari, A. Linearized two-layers neural networks in high dimension. Ann. Stat. 49, 1029 \u2013 1054 (2021).","journal-title":"Ann. Stat."},{"key":"767_CR52","doi-asserted-by":"publisher","first-page":"064309","DOI":"10.1103\/PhysRevE.105.064309","volume":"105","author":"S Ariosto","year":"2022","unstructured":"Ariosto, S., Pacelli, R., Ginelli, F., Gherardi, M. & Rotondo, P. Universal mean-field upper bound for the generalization gap of deep neural networks. Phys. Rev. E 105, 064309 (2022).","journal-title":"Phys. Rev. E"},{"key":"767_CR53","unstructured":"Shah, A., Wilson, A. & Ghahramani, Z. Student-t processes as alternatives to Gaussian processes. In Proc. 17th International Conference on Artificial Intelligence and Statistics (eds Kaski, S. & Corander, J.) 877\u2013885 (PMLR, 2014)."},{"key":"767_CR54","doi-asserted-by":"crossref","unstructured":"Zavatone-Veth, J. A., Canatar, A., Ruben, B. S. & Pehlevan, C. Asymptotics of representation learning in finite Bayesian neural networks. J. Stat. Mech. 2022, 114008 (2022).","DOI":"10.1088\/1742-5468\/ac98a6"},{"key":"767_CR55","doi-asserted-by":"crossref","unstructured":"Hanin, B. & Zlokapa, A. Bayesian interpolation with deep linear networks. Proc. Natl Acad. Sci. 120, e2301345120 (2023).","DOI":"10.1073\/pnas.2301345120"},{"key":"767_CR56","doi-asserted-by":"publisher","first-page":"365001","DOI":"10.1088\/1751-8121\/aba028","volume":"53","author":"ACC Coolen","year":"2020","unstructured":"Coolen, A. C. C., Sheikh, M., Mozeika, A., Aguirre-L\u00f3pez, F. & Antenucci, F. Replica analysis of overfitting in generalized linear regression models. J. Phys. A 53, 365001 (2020).","journal-title":"J. Phys. A"},{"key":"767_CR57","doi-asserted-by":"publisher","first-page":"042142","DOI":"10.1103\/PhysRevE.103.042142","volume":"103","author":"A Mozeika","year":"2021","unstructured":"Mozeika, A., Sheikh, M., Aguirre-L\u00f3pez, F., Antenucci, F. & Coolen, A. C. C. Exact results on high-dimensional linear regression via statistical physics. Phys. Rev. E 103, 042142 (2021).","journal-title":"Phys. Rev. E"},{"key":"767_CR58","doi-asserted-by":"publisher","first-page":"1","DOI":"10.5687\/sss.2021.1","volume":"2021","author":"Y Uchiyama","year":"2021","unstructured":"Uchiyama, Y., Oka, H. & Nono, A. Student\u2019s t-process regression on the space of probability density functions. Proc. ISCIE International Symposium on Stochastic Systems Theory and its Applications 2021, 1\u20135 (2021).","journal-title":"Proc. ISCIE International Symposium on Stochastic Systems Theory and its Applications"},{"key":"767_CR59","unstructured":"Lee, H., Yun, E., Yang, H. & Lee, J. Scale mixtures of neural network Gaussian processes. In International Conference on Learning Representations (ICLR, 2022)."},{"key":"767_CR60","unstructured":"Aitchison, L. Why bigger is not always better: on finite and infinite neural networks. In Proc. 37th International Conference on Machine Learning (eds Daum\u00e9, H. III & Singh, A.) 156\u2013164 (PMLR, 2020)."},{"key":"767_CR61","doi-asserted-by":"crossref","unstructured":"Zavatone-Veth, J. A. & Pehlevan, C. Depth induces scale-averaging in overparameterized linear Bayesian neural networks. In 2021 55th Asilomar Conference on Signals, Systems, and Computers 600\u2013607 (IEEE, 2021).","DOI":"10.1109\/IEEECONF53345.2021.9723137"},{"key":"767_CR62","unstructured":"Yang, A. X., Robeyns, M., Milsom, E., Schoots, N. & Aitchison, L. A theory of representation learning in deep neural networks gives a deep generalisation of kernel methods. Preprint at https:\/\/arxiv.org\/abs\/2108.13097 (2023)."},{"key":"767_CR63","unstructured":"Cho, Y. & Saul, L. Kernel methods for deep learning. In Advances in Neural Information Processing Systems (eds Bengio, Y. et al.) Vol. 22 (Curran Associates, 2009)."},{"key":"767_CR64","unstructured":"Poole, B., Lahiri, S., Raghu, M., Sohl-Dickstein, J. & Ganguli, S. Exponential expressivity in deep neural networks through transient chaos. In Advances in Neural Information Processing Systems (eds Garnett, R. et al.) Vol. 29 (Curran Associates, 2016)."},{"key":"767_CR65","unstructured":"Yang, G. & Schoenholz, S. Mean field residual networks: on the edge of chaos. In Advances in Neural Information Processing Systems (eds Guyon, I. et al.) Vol. 30 (Curran Associates, 2017)."},{"key":"767_CR66","doi-asserted-by":"crossref","unstructured":"Tracey, B. D. & Wolpert, D. Upgrading from Gaussian processes to Student\u2019s-t processes. In 2018 AIAA Non-Deterministic Approaches Conference 1659 (2018).","DOI":"10.2514\/6.2018-1659"},{"key":"767_CR67","doi-asserted-by":"crossref","unstructured":"Roberts, D. A., Yaida, S. & Hanin, B. The Principles of Deep Learning Theory (Cambridge Univ. Press, 2022).","DOI":"10.1017\/9781009023405"},{"key":"767_CR68","unstructured":"Gerace, F., Krzakala, F., Loureiro, B., Stephan, L. & Zdeborov\u00e1, L. Gaussian universality of linear classifiers with random labels in high-dimension. Preprint at https:\/\/arxiv.org\/abs\/2205.13303 (2022)."},{"key":"767_CR69","unstructured":"Cui, H., Krzakala, F. & Zdeborov\u00e1, L. Bayes-optimal learning of deep random networks of extensive-width. In Proc. 40th International Conference on Machine Learning (eds Krause, A. et al.) 6468\u20136521 (PMLR, 2023)."},{"key":"767_CR70","unstructured":"Lee, J. et al. Finite versus infinite neural networks: an empirical study. In Advances in Neural Information Processing Systems (eds Lin, H. et al.) 15156\u201315172 (Curran Associates, 2020)."},{"key":"767_CR71","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1016\/j.jcp.2019.01.045","volume":"384","author":"G Pang","year":"2019","unstructured":"Pang, G., Yang, L. & Karniadakis, G. E. Neural-net-induced Gaussian process regression for function approximation and PDE solution. J. Comput. Phys. 384, 270\u2013288 (2019).","journal-title":"J. Comput. Phys."},{"key":"767_CR72","unstructured":"Krizhevsky, A. Learning Multiple Layers of Features from Tiny Images (Univ. Toronto, 2012)."},{"key":"767_CR73","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y Lecun","year":"1998","unstructured":"Lecun, Y., Bottou, L., Bengio, Y. & Haffner, P. Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278\u20132324 (1998).","journal-title":"Proc. IEEE"},{"key":"767_CR74","unstructured":"Pacelli, R. rpacelli\/FC_deep_bayesian_networks: FC_deep_bayesian_networks (2023)."}],"container-title":["Nature Machine Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00767-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00767-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00767-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,18]],"date-time":"2023-12-18T20:09:54Z","timestamp":1702930194000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00767-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,18]]},"references-count":74,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["767"],"URL":"https:\/\/doi.org\/10.1038\/s42256-023-00767-6","relation":{},"ISSN":["2522-5839"],"issn-type":[{"value":"2522-5839","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,18]]},"assertion":[{"value":"21 October 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 October 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 December 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}