{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:56:30Z","timestamp":1772758590418,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":76,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,6,10]],"date-time":"2022-06-10T00:00:00Z","timestamp":1654819200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,6,10]]},"DOI":"10.1145\/3514221.3526156","type":"proceedings-article","created":{"date-parts":[[2022,6,12]],"date-time":"2022-06-12T02:33:49Z","timestamp":1655001229000},"page":"973-987","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":23,"title":["Lightweight and Accurate Cardinality Estimation by Neural Network Gaussian Process"],"prefix":"10.1145","author":[{"given":"Kangfei","family":"Zhao","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong S. A. R., China"}]},{"given":"Jeffrey Xu","family":"Yu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong S. A. R., China"}]},{"given":"Zongyan","family":"He","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong S. A. R., China"}]},{"given":"Rui","family":"Li","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong S. A. R., China"}]},{"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong S. A. R., China"}]}],"member":"320","published-online":{"date-parts":[[2022,6,11]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Pytorch. https:\/\/github.com\/pytorch\/pytorch."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/304182.304581"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2593667"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3064029"},{"key":"e_1_3_2_1_5_1","volume-title":"Pattern recognition and machine learning","author":"Bishop C. M.","year":"2007","unstructured":"C. M. Bishop. Pattern recognition and machine learning, 5th Edition. Information science and statistics. Springer, 2007.","edition":"5"},{"key":"e_1_3_2_1_6_1","volume-title":"JAX: composable transformations of Python+NumPy programs","author":"Bradbury J.","year":"2018","unstructured":"J. Bradbury, R. Frostig, P. Hawkins, M. J. Johnson, C. Leary, D. Maclaurin, G. Necula, A. Paszke, J. VanderPlas, S. Wanderman-Milne, and Q. Zhang. JAX: composable transformations of Python+NumPy programs, 2018."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3319894"},{"key":"e_1_3_2_1_8_1","first-page":"6946","volume-title":"Proc. NIPS'19","author":"Chen J.","year":"2017","unstructured":"J. Chen, M. Stern, M. J. Wainwright, and M. I. Jordan. Kernel feature selection via conditional covariance minimization. In Proc. NIPS'19, pages 6946--6955, 2017."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_2_1_10_1","first-page":"342","volume-title":"Proc. NIPS'09","author":"Cho Y.","year":"2009","unstructured":"Y. Cho and L. K. Saul. Kernel methods for deep learning. In Proc. NIPS'09, pages 342--350, 2009."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3324957"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389711"},{"key":"e_1_3_2_1_13_1","volume-title":"UCI machine learning repository","author":"Dua D.","year":"2017","unstructured":"D. Dua and C. Graff. UCI machine learning repository, 2017."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.14778\/1687627.1687767"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.14778\/3407790.3407820"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.14778\/3329772.3329780"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389745"},{"key":"e_1_3_2_1_18_1","volume-title":"Bayesian convolutional neural networks with bernoulli approximate variational inference. CoRR, abs\/1506.02158","author":"Gal Y.","year":"2015","unstructured":"Y. Gal and Z. Ghahramani. Bayesian convolutional neural networks with bernoulli approximate variational inference. CoRR, abs\/1506.02158, 2015."},{"key":"e_1_3_2_1_19_1","first-page":"1050","volume-title":"Proc. ICML'16","volume":"48","author":"Gal Y.","year":"2016","unstructured":"Y. Gal and Z. Ghahramani. Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In Proc. ICML'16, volume 48, pages 1050--1059, 2016."},{"key":"e_1_3_2_1_20_1","volume-title":"Proc. ICLR'19","author":"Garriga-Alonso A.","year":"2019","unstructured":"A. Garriga-Alonso, C. E. Rasmussen, and L. Aitchison. Deep convolutional networks as shallow gaussian processes. In Proc. ICLR'19, 2019."},{"key":"e_1_3_2_1_21_1","first-page":"881","volume-title":"Proc. ICML'15","volume":"37","author":"Germain M.","year":"2015","unstructured":"M. Germain, K. Gregor, I. Murray, and H. Larochelle. MADE: masked autoencoder for distribution estimation. In Proc. ICML'15, volume 37, pages 881--889, 2015."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/375663.375727"},{"key":"e_1_3_2_1_23_1","volume-title":"Proc. ICLR","author":"Goodfellow I. J.","year":"2015","unstructured":"I. J. Goodfellow, J. Shlens, and C. Szegedy. Explaining and harnessing adversarial examples. In Proc. ICLR, 2015."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-003-0090-4"},{"key":"e_1_3_2_1_25_1","first-page":"1321","volume-title":"Proc. ICML'17","volume":"70","author":"Guo C.","year":"2017","unstructured":"C. Guo, G. Pleiss, Y. Sun, and K. Q. Weinberger. On calibration of modern neural networks. In Proc. ICML'17, volume 70, pages 1321--1330. PMLR, 2017."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/304181.304208"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389741"},{"issue":"7","key":"e_1_3_2_1_28_1","first-page":"992","article-title":"Deepdb: Learn from data, not from queries! Proc","volume":"13","author":"Hilprecht B.","year":"2020","unstructured":"B. Hilprecht, A. Schmidt, M. Kulessa, A. Molina, K. Kersting, and C. Binnig. Deepdb: Learn from data, not from queries! Proc. VLDB, 13(7):992--1005, 2020.","journal-title":"VLDB"},{"key":"e_1_3_2_1_29_1","first-page":"4376","volume-title":"Proc. ICML'20","volume":"119","author":"Hron J.","year":"2020","unstructured":"J. Hron, Y. Bahri, J. Sohl-Dickstein, and R. Novak. Infinite attention: NNGP and NTK for deep attention networks. In Proc. ICML'20, volume 119, pages 4376--4386. PMLR, 2020."},{"key":"e_1_3_2_1_30_1","volume-title":"Infinitely wide graph convolutional networks: Semi-supervised learning via gaussian processes. CoRR, abs\/2002.12168","author":"Hu J.","year":"2020","unstructured":"J. Hu, J. Shen, B. Yang, and L. Shao. Infinitely wide graph convolutional networks: Semi-supervised learning via gaussian processes. CoRR, abs\/2002.12168, 2020."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05318-5"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.14778\/3151106.3151112"},{"key":"e_1_3_2_1_33_1","volume-title":"Proc. CIDR'19","author":"Kipf A.","year":"2019","unstructured":"A. Kipf, T. Kipf, B. Radke, V. Leis, P. A. Boncz, and A. Kemper. Learned cardinalities: Estimating correlated joins with deep learning. In Proc. CIDR'19, 2019."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3196909"},{"key":"e_1_3_2_1_35_1","volume-title":"Learning to optimize join queries with deep reinforcement learning. CoRR, abs\/1808.03196","author":"Krishnan S.","year":"2018","unstructured":"S. Krishnan, Z. Yang, K. Goldberg, J. M. Hellerstein, and I. Stoica. Learning to optimize join queries with deep reinforcement learning. CoRR, abs\/1808.03196, 2018."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3380591"},{"key":"e_1_3_2_1_37_1","first-page":"6402","volume-title":"Proc. NIPS'17","author":"Lakshminarayanan B.","year":"2017","unstructured":"B. Lakshminarayanan, A. Pritzel, and C. Blundell. Simple and scalable predictive uncertainty estimation using deep ensembles. In Proc. NIPS'17, pages 6402--6413, 2017."},{"key":"e_1_3_2_1_38_1","volume-title":"SIAM","author":"Lee H. K.","year":"2004","unstructured":"H. K. Lee. Bayesian nonparametrics via neural networks. SIAM, 2004."},{"key":"e_1_3_2_1_39_1","volume-title":"Proc. ICLR'18","author":"Lee J.","year":"2018","unstructured":"J. Lee, Y. Bahri, R. Novak, S. S. Schoenholz, J. Pennington, and J. Sohl-Dickstein. Deep neural networks as gaussian processes. In Proc. ICLR'18, 2018."},{"key":"e_1_3_2_1_40_1","first-page":"8570","volume-title":"Proc. NeurIPS","author":"Lee J.","year":"2019","unstructured":"J. Lee, L. Xiao, S. S. Schoenholz, Y. Bahri, R. Novak, J. Sohl-Dickstein, and J. Pennington. Wide neural networks of any depth evolve as linear models under gradient descent. In Proc. NeurIPS, pages 8570--8581, 2019."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.14778\/2850583.2850594"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50026-X"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2915235"},{"key":"e_1_3_2_1_44_1","volume-title":"Opportunistic view materialization with deep reinforcement learning. CoRR, abs\/1903.01363","author":"Liang X.","year":"2019","unstructured":"X. Liang, A. J. Elmore, and S. Krishnan. Opportunistic view materialization with deep reinforcement learning. CoRR, abs\/1903.01363, 2019."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.14778\/3476249.3476254"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3324958"},{"key":"e_1_3_2_1_47_1","volume-title":"NATO ASI series F computer and systems sciences, 168:133--166","author":"MacKay D. J.","year":"1998","unstructured":"D. J. MacKay. Introduction to gaussian processes. NATO ASI series F computer and systems sciences, 168:133--166, 1998."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3384706"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.14778\/3342263.3342644"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9538"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3380579"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-0745-0_2"},{"key":"e_1_3_2_1_53_1","volume-title":"Proc. ICLR'19","author":"Novak R.","year":"2019","unstructured":"R. Novak, L. Xiao, Y. Bahri, J. Lee, G. Yang, J. Hron, D. A. Abolafia, J. Pennington, and J. Sohl-Dickstein. Bayesian deep convolutional networks with many channels are gaussian processes. In Proc. ICLR'19, 2019."},{"key":"e_1_3_2_1_54_1","volume-title":"Proc. ICLR'20","author":"Novak R.","year":"2020","unstructured":"R. Novak, L. Xiao, J. Hron, J. Lee, A. A. Alemi, J. Sohl-Dickstein, and S. S. Schoenholz. Neural tangents: Fast and easy infinite neural networks in python. In Proc. ICLR'20, 2020."},{"key":"e_1_3_2_1_55_1","first-page":"486","volume-title":"Proc. VLDB'97","author":"Poosala V.","year":"1997","unstructured":"V. Poosala and Y. E. Ioannidis. Selectivity estimation without the attribute value independence assumption. In Proc. VLDB'97, pages 486--495, 1997."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/233269.233342"},{"key":"e_1_3_2_1_57_1","volume-title":"Gaussian processes for machine learning","author":"Rasmussen C. E.","year":"2006","unstructured":"C. E. Rasmussen and C. K. I. Williams. Gaussian processes for machine learning. MIT Press, 2006."},{"key":"e_1_3_2_1_58_1","volume-title":"Synthesis Lectures on Artificial Intelligence and Machine Learning","author":"Settles B.","year":"2012","unstructured":"B. Settles. Active Learning. Synthesis Lectures on Artificial Intelligence and Machine Learning. Morgan & Claypool Publishers, 2012."},{"key":"e_1_3_2_1_59_1","first-page":"1393","article-title":"Feature selection via dependence maximization","volume":"13","author":"Song L.","year":"2012","unstructured":"L. Song, A. J. Smola, A. Gretton, J. Bedo, and K. M. Borgwardt. Feature selection via dependence maximization. J. Mach. Learn. Res., 13:1393--1434, 2012.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.14778\/3368289.3368296"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE48307.2020.00117"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719574"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.14778\/3402707.3402724"},{"key":"e_1_3_2_1_64_1","first-page":"5998","volume-title":"Proc. NeurIPS'17","author":"Vaswani A.","year":"2017","unstructured":"A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin. Attention is all you need. In Proc. NeurIPS'17, pages 5998--6008, 2017."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2016.2606428"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.14778\/3461535.3461552"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300017412"},{"key":"e_1_3_2_1_68_1","volume-title":"Proc. NeurIPS'20","author":"Wilson A. G.","year":"2020","unstructured":"A. G. Wilson and P. Izmailov. Bayesian deep learning and a probabilistic perspective of generalization. In Proc. NeurIPS'20, 2020."},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017322"},{"key":"e_1_3_2_1_70_1","first-page":"9947","volume-title":"Proc. NeurIPS'19","author":"Yang G.","year":"2019","unstructured":"G. Yang. Wide feedforward or recurrent neural networks of any architecture are gaussian processes. In Proc. NeurIPS'19, pages 9947--9960, 2019."},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.14778\/3421424.3421432"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.14778\/3368289.3368294"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3300085"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457289"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3183739"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.14778\/3397230.3397238"}],"event":{"name":"SIGMOD\/PODS '22: International Conference on Management of Data","location":"Philadelphia PA USA","acronym":"SIGMOD\/PODS '22","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 2022 International Conference on Management of Data"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3514221.3526156","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3514221.3526156","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:10:13Z","timestamp":1750183813000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3514221.3526156"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,10]]},"references-count":76,"alternative-id":["10.1145\/3514221.3526156","10.1145\/3514221"],"URL":"https:\/\/doi.org\/10.1145\/3514221.3526156","relation":{},"subject":[],"published":{"date-parts":[[2022,6,10]]},"assertion":[{"value":"2022-06-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}