@inproceedings{boser1992,
	added-at = {2011-04-06T14:59:36.000+0200},
	address = {Pittsburgh, PA, USA},
	author = {Boser, Bernhard E. and Guyon, Isabelle M. and Vapnik, Vladimir N.},
	biburl = {https://www.bibsonomy.org/bibtex/2f4c8abb0eea7de4431f51c6dd3f3eb55/utahell},
	booktitle = {Proceedings of the 5th Annual Workshop on Computational Learning Theory (COLT'92)},
	description = {A training algorithm for optimal margin classifiers},
	editor = {Haussler, David},
	interhash = {81c1ca02cfdb4006d4ae602fcbbafcd3},
	intrahash = {f4c8abb0eea7de4431f51c6dd3f3eb55},
	keywords = {learning svm},
	month = {July},
	pages = {144--152},
	publisher = {ACM Press},
	timestamp = {2011-12-16T16:31:14.000+0100},
	title = {A Training Algorithm for Optimal Margin Classifiers},
	url = {http://doi.acm.org/10.1145/130385.130401},
	year = 1992
}

@article{Gai_piecewise,
	added-at = {2018-08-13T00:00:00.000+0200},
	author = {Gai, Kun and Zhu, Xiaoqiang and Li, Han and Liu, Kai and Wang, Zhe},
	biburl = {https://www.bibsonomy.org/bibtex/20a9312f3a5b0481928e589477d7dee81/dblp},
	ee = {http://arxiv.org/abs/1704.05194},
	interhash = {2c5f2e3b8e0a358d4b4d24835a6b5a33},
	intrahash = {0a9312f3a5b0481928e589477d7dee81},
	journal = {CoRR},
	keywords = {dblp},
	timestamp = {2018-08-14T13:15:00.000+0200},
	title = {Learning Piece-wise Linear Models from Large Scale Data for Ad Click Prediction.},
	url = {http://dblp.uni-trier.de/db/journals/corr/corr1704.html#GaiZLLW17},
	volume = {abs/1704.05194},
	year = 2017
}

@article{lecun_sgd,
	abstract = {Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradient based learning technique. Given an appropriate network architecture, gradient-based learning algorithms can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters, with minimal preprocessing. This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task. Convolutional neural networks, which are specifically designed to deal with the variability of 2D shapes, are shown to outperform all other techniques. Real-life document recognition systems are composed of multiple modules including field extraction, segmentation recognition, and language modeling. A new learning paradigm, called graph transformer networks (GTN), allows such multimodule systems to be trained globally using gradient-based methods so as to minimize an overall performance measure. Two systems for online handwriting recognition are described. Experiments demonstrate the advantage of global training, and the flexibility of graph transformer networks. A graph transformer network for reading a bank cheque is also described. It uses convolutional neural network character recognizers combined with global training techniques to provide record accuracy on business and personal cheques. It is deployed commercially and reads several million cheques per day},
	added-at = {2019-01-05T14:54:07.000+0100},
	author = {LeCun, Y. and Bottou, L. and Bengio, Y. and Haffner, P.},
	biburl = {https://www.bibsonomy.org/bibtex/28417f8e20e96a98703486b82a09583c7/slicside},
	doi = {10.1109/5.726791},
	interhash = {7a82cccacd23cf06b25ff5325a6c86c7},
	intrahash = {8417f8e20e96a98703486b82a09583c7},
	issn = {0018-9219},
	journal = {Proceedings of the IEEE},
	keywords = {ba-2018-hahnrico},
	number = 11,
	pages = {2278-2324},
	timestamp = {2019-01-05T14:54:07.000+0100},
	title = {Gradient-based learning applied to document recognition},
	volume = 86,
	year = 1998
}
@article{lbfgs_2008,
	added-at = {2020-02-17T00:00:00.000+0100},
	author = {Xiao, Yunhai and Wei, Zengxin and Wang, Zhiguo},
	biburl = {https://www.bibsonomy.org/bibtex/29a414487321cd8049eb9f34c3e8e2e61/dblp},
	ee = {https://doi.org/10.1016/j.camwa.2008.01.028},
	interhash = {d843677026f4d5722d2500525d47b5ca},
	intrahash = {9a414487321cd8049eb9f34c3e8e2e61},
	journal = {Comput. Math. Appl.},
	keywords = {dblp},
	number = 4,
	pages = {1001-1009},
	timestamp = {2020-02-18T11:38:42.000+0100},
	title = {A limited memory BFGS-type method for large-scale unconstrained optimization.},
	url = {http://dblp.uni-trier.de/db/journals/cma/cma56.html#XiaoWW08},
	volume = 56,
	year = 2008
}

@inproceedings{Graepel_2010,
	added-at = {2019-04-03T00:00:00.000+0200},
	author = {Graepel, Thore and Candela, Joaquin Quiñonero and Borchert, Thomas and Herbrich, Ralf},
	biburl = {https://www.bibsonomy.org/bibtex/2b008aa80a83b88a6e5fee59caa9b6493/dblp},
	booktitle = {ICML},
	crossref = {conf/icml/2010},
	editor = {Fürnkranz, Johannes and Joachims, Thorsten},
	ee = {https://icml.cc/Conferences/2010/papers/901.pdf},
	interhash = {2a83b4cd23188992c5b7a4023eedcebe},
	intrahash = {b008aa80a83b88a6e5fee59caa9b6493},
	keywords = {dblp},
	pages = {13-20},
	publisher = {Omnipress},
	timestamp = {2019-04-04T11:48:32.000+0200},
	title = {Web-Scale Bayesian Click-Through rate Prediction for Sponsored Search Advertising in Microsoft's Bing Search Engine.},
	url = {http://dblp.uni-trier.de/db/conf/icml/icml2010.html#GraepelCBH10},
	year = 2010
}

@inproceedings{Rendle:2010ja,
	added-at = {2019-05-21T10:10:49.000+0200},
	author = {Rendle, Steffen},
	biburl = {https://www.bibsonomy.org/bibtex/265ab448242aaaeb060a8b9ed87204423/sxkdz},
	booktitle = {Proceedings of the 2010 IEEE International Conference on Data Mining},
	doi = {10.1109/ICDM.2010.127},
	interhash = {425e17658c7386e5b35c505a1ed89aff},
	intrahash = {65ab448242aaaeb060a8b9ed87204423},
	issn = {2374-8486},
	keywords = {imported},
	month = dec,
	pages = {995--1000},
	publisher = {IEEE},
	series = {ICDM '10},
	timestamp = {2019-05-21T10:10:49.000+0200},
	title = {{Factorization Machines}},
	url = {http://ieeexplore.ieee.org/document/5694074/},
	year = 2010
}

@inproceedings{Juan_fieldawarefm1,
	added-at = {2018-11-06T00:00:00.000+0100},
	author = {Juan, Yu-Chin and Zhuang, Yong and Chin, Wei-Sheng and Lin, Chih-Jen},
	biburl = {https://www.bibsonomy.org/bibtex/2fbb5958a0b0b3ab03c7423e84cc08d9c/dblp},
	booktitle = {RecSys},
	crossref = {conf/recsys/2016},
	editor = {Sen, Shilad and Geyer, Werner and Freyne, Jill and Castells, Pablo},
	ee = {https://doi.org/10.1145/2959100.2959134},
	interhash = {b512083d1729eed87424afe44ebc8677},
	intrahash = {fbb5958a0b0b3ab03c7423e84cc08d9c},
	isbn = {978-1-4503-4035-9},
	keywords = {dblp},
	pages = {43-50},
	publisher = {ACM},
	timestamp = {2018-11-07T12:40:54.000+0100},
	title = {Field-aware Factorization Machines for CTR Prediction.},
	url = {http://dblp.uni-trier.de/db/conf/recsys/recsys2016.html#JuanZCL16},
	year = 2016
}

@article{Juan_fieldawarefm2,
	added-at = {2018-08-13T00:00:00.000+0200},
	author = {Juan, Yuchin and Lefortier, Damien and Chapelle, Olivier},
	biburl = {https://www.bibsonomy.org/bibtex/29ef509381d1eb3ebd24239efc195f9fb/dblp},
	ee = {http://arxiv.org/abs/1701.04099},
	interhash = {1a419341131eb2bc20e6ac71713d7a6d},
	intrahash = {9ef509381d1eb3ebd24239efc195f9fb},
	journal = {CoRR},
	keywords = {dblp},
	timestamp = {2018-08-14T13:16:14.000+0200},
	title = {Field-aware Factorization Machines in a Real-world Online Advertising System.},
	url = {http://dblp.uni-trier.de/db/journals/corr/corr1701.html#JuanLC17},
	volume = {abs/1701.04099},
	year = 2017
}

@article{Pan_fieldweightedfm,
	added-at = {2018-08-13T00:00:00.000+0200},
	author = {Pan, Junwei and Xu, Jian and Ruiz, Alfonso Lobos and Zhao, Wenliang and Pan, Shengjun and Sun, Yu and Lu, Quan},
	biburl = {https://www.bibsonomy.org/bibtex/203e245bd5b30499fbdd6ff6b60c4b022/dblp},
	ee = {http://arxiv.org/abs/1806.03514},
	interhash = {13c7bf6b08564f96ec471e2b42a90218},
	intrahash = {03e245bd5b30499fbdd6ff6b60c4b022},
	journal = {CoRR},
	keywords = {dblp},
	timestamp = {2018-08-14T13:11:25.000+0200},
	title = {Field-weighted Factorization Machines for Click-Through Rate Prediction in Display Advertising.},
	url = {http://dblp.uni-trier.de/db/journals/corr/corr1806.html#abs-1806-03514},
	volume = {abs/1806.03514},
	year = 2018
}

@inproceedings{Pan_sparsefm,
	added-at = {2019-02-11T00:00:00.000+0100},
	author = {Pan, Zhen and Chen, Enhong and Liu, Qi and Xu, Tong and Ma, Haiping and Lin, Hongjie},
	biburl = {https://www.bibsonomy.org/bibtex/2a22be9a0667f11266d704e178d8a2b6e/dblp},
	booktitle = {ICDM},
	crossref = {conf/icdm/2016},
	editor = {Bonchi, Francesco and Domingo-Ferrer, Josep and Baeza-Yates, Ricardo and Zhou, Zhi-Hua and Wu, Xindong},
	ee = {http://doi.ieeecomputersociety.org/10.1109/ICDM.2016.0051},
	interhash = {639e5eb01646b897aeb0dc3257588811},
	intrahash = {a22be9a0667f11266d704e178d8a2b6e},
	keywords = {dblp},
	pages = {400-409},
	publisher = {IEEE Computer Society},
	timestamp = {2019-10-17T13:02:53.000+0200},
	title = {Sparse Factorization Machines for Click-through Rate Prediction.},
	url = {http://dblp.uni-trier.de/db/conf/icdm/icdm2016.html#PanCLXML16},
	year = 2016
}

@inproceedings{Freudenthaler2011BayesianFM,
	title={Bayesian Factorization Machines},
	author={Freudenthaler, C., Schmidt-Thieme, L., and Rendle, S},
	booktitle={In Proceedings of the NIPS Workshop on Sparse Representation and Low-rank Approximation},
	year={2011}
}

@article{Xiao_afm,
	added-at = {2018-08-13T00:00:00.000+0200},
	author = {Xiao, Jun and Ye, Hao and He, Xiangnan and Zhang, Hanwang and Wu, Fei and Chua, Tat-Seng},
	biburl = {https://www.bibsonomy.org/bibtex/2b66b4732b35617644835daba33d1a916/dblp},
	ee = {http://arxiv.org/abs/1708.04617},
	interhash = {4f5c499774291dc0e9184e781c365c05},
	intrahash = {b66b4732b35617644835daba33d1a916},
	journal = {CoRR},
	keywords = {dblp},
	timestamp = {2018-08-14T13:52:58.000+0200},
	title = {Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks.},
	url = {http://dblp.uni-trier.de/db/journals/corr/corr1708.html#abs-1708-04617},
	volume = {abs/1708.04617},
	year = 2017
}

@article{srivastava2014dropout,
	abstract = {{Deep neural nets with a large number of parameters are very powerful machine learning systems. However, overfitting is a serious problem in such networks. Large networks are also slow to use, making it difficult to deal with overfitting by combining the predictions of many different large neural nets at test time. Dropout is a technique for addressing this problem. The key idea is to randomly drop units (along with their connections) from the neural network during training. This prevents units from co-adapting too much. During training, dropout samples from an exponential number of different "thinned" networks. At test time, it is easy to approximate the effect of averaging the predictions of all these thinned networks by simply using a single unthinned network that has smaller weights. This significantly reduces overfitting and gives major improvements over other regularization methods. We show that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets.}},
	added-at = {2017-07-19T15:29:59.000+0200},
	author = {Srivastava, Nitish and Hinton, Geoffrey and Krizhevsky, Alex and Sutskever, Ilya and Salakhutdinov, Ruslan},
	biburl = {https://www.bibsonomy.org/bibtex/20715644d640cdaad9258133625cc5fe9/andreashdez},
	citeulike-article-id = {13833631},
	citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=2670313},
	interhash = {bdad866eb5fd8994c2aeae46af6def20},
	intrahash = {0715644d640cdaad9258133625cc5fe9},
	issn = {1532-4435},
	journal = {J. Mach. Learn. Res.},
	keywords = {imported},
	month = jan,
	number = 1,
	pages = {1929--1958},
	posted-at = {2016-04-29 18:36:35},
	priority = {0},
	publisher = {JMLR.org},
	timestamp = {2017-07-19T15:31:02.000+0200},
	title = {{Dropout: A Simple Way to Prevent Neural Networks from Overfitting}},
	url = {http://portal.acm.org/citation.cfm?id=2670313},
	volume = 15,
	year = 2014
}

@inproceedings{tikhonov1943stability,
	title={On the stability of inverse problems},
	author={Tikhonov, Andrey Nikolayevich},
	booktitle={Dokl. Akad. Nauk SSSR},
	volume={39},
	pages={195--198},
	year={1943}
}

@inproceedings{Chen_deepctr,
	added-at = {2020-04-08T00:00:00.000+0200},
	author = {Chen, Junxuan and Sun, Baigui and Li, Hao and Lu, Hongtao and Hua, Xian-Sheng},
	biburl = {https://www.bibsonomy.org/bibtex/2381b8348cc449d46692ef7e7830a51b7/dblp},
	booktitle = {ACM Multimedia},
	crossref = {conf/mm/2016},
	editor = {Hanjalic, Alan and Snoek, Cees and Worring, Marcel and Bulterman, Dick C. A. and Huet, Benoit and Kelliher, Aisling and Kompatsiaris, Yiannis and Li, Jin},
	ee = {https://doi.org/10.1145/2964284.2964325},
	interhash = {f065025197d2320d883e2cc079fa7ac6},
	intrahash = {381b8348cc449d46692ef7e7830a51b7},
	isbn = {978-1-4503-3603-1},
	keywords = {dblp},
	pages = {811-820},
	publisher = {ACM},
	timestamp = {2020-04-09T11:42:00.000+0200},
	title = {Deep CTR Prediction in Display Advertising.},
	url = {http://dblp.uni-trier.de/db/conf/mm/mm2016.html#ChenSLLH16},
	year = 2016
}

@misc{he2015residual,
	abstract = {Deeper neural networks are more difficult to train. We present a residual
	learning framework to ease the training of networks that are substantially
	deeper than those used previously. We explicitly reformulate the layers as
	learning residual functions with reference to the layer inputs, instead of
	learning unreferenced functions. We provide comprehensive empirical evidence
	showing that these residual networks are easier to optimize, and can gain
	accuracy from considerably increased depth. On the ImageNet dataset we evaluate
	residual nets with a depth of up to 152 layers---8x deeper than VGG nets but
	still having lower complexity. An ensemble of these residual nets achieves
	3.57% error on the ImageNet test set. This result won the 1st place on the
	ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100
	and 1000 layers.
	The depth of representations is of central importance for many visual
	recognition tasks. Solely due to our extremely deep representations, we obtain
	a 28% relative improvement on the COCO object detection dataset. Deep residual
	nets are foundations of our submissions to ILSVRC & COCO 2015 competitions,
	where we also won the 1st places on the tasks of ImageNet detection, ImageNet
	localization, COCO detection, and COCO segmentation.},
	added-at = {2017-05-15T22:38:25.000+0200},
	author = {He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
	biburl = {https://www.bibsonomy.org/bibtex/2d0b3536c45de7324284739a24006de6a/axel.vogler},
	description = {Deep Residual Learning for Image Recognition},
	interhash = {3066b045c86a0b721a053f73eb50cd95},
	intrahash = {d0b3536c45de7324284739a24006de6a},
	keywords = {deep-learning res-net},
	note = {cite arxiv:1512.03385Comment: Tech report},
	timestamp = {2017-05-15T22:38:25.000+0200},
	title = {Deep Residual Learning for Image Recognition},
	url = {http://arxiv.org/abs/1512.03385},
	year = 2015
}

@inproceedings{Nair_relu,
	added-at = {2019-04-03T00:00:00.000+0200},
	author = {Nair, Vinod and Hinton, Geoffrey E.},
	biburl = {https://www.bibsonomy.org/bibtex/2059683ca9b2457d248942520babbe000/dblp},
	booktitle = {ICML},
	crossref = {conf/icml/2010},
	editor = {Fürnkranz, Johannes and Joachims, Thorsten},
	ee = {https://icml.cc/Conferences/2010/papers/432.pdf},
	interhash = {acefcb0a5d1a937232f02f3fe0d5ab86},
	intrahash = {059683ca9b2457d248942520babbe000},
	keywords = {dblp},
	pages = {807-814},
	publisher = {Omnipress},
	timestamp = {2019-04-04T11:48:32.000+0200},
	title = {Rectified Linear Units Improve Restricted Boltzmann Machines.},
	url = {http://dblp.uni-trier.de/db/conf/icml/icml2010.html#NairH10},
	year = 2010
}

@article{Guo_embedding_2016,
	added-at = {2018-08-13T00:00:00.000+0200},
	author = {Guo, Cheng and Berkhahn, Felix},
	biburl = {https://www.bibsonomy.org/bibtex/24f27494e7e90a5cbe32c726f3b729495/dblp},
	ee = {http://arxiv.org/abs/1604.06737},
	interhash = {6e2f004f0eaeff1b3ae92bbb7662dc33},
	intrahash = {4f27494e7e90a5cbe32c726f3b729495},
	journal = {CoRR},
	keywords = {dblp},
	timestamp = {2018-08-14T13:14:38.000+0200},
	title = {Entity Embeddings of Categorical Variables.},
	url = {http://dblp.uni-trier.de/db/journals/corr/corr1604.html#GuoB16},
	volume = {abs/1604.06737},
	year = 2016
}

@misc{ioffe2015batch,
	abstract = {Training Deep Neural Networks is complicated by the fact that the
	distribution of each layer's inputs changes during training, as the parameters
	of the previous layers change. This slows down the training by requiring lower
	learning rates and careful parameter initialization, and makes it notoriously
	hard to train models with saturating nonlinearities. We refer to this
	phenomenon as internal covariate shift, and address the problem by normalizing
	layer inputs. Our method draws its strength from making normalization a part of
	the model architecture and performing the normalization for each training
	mini-batch. Batch Normalization allows us to use much higher learning rates and
	be less careful about initialization. It also acts as a regularizer, in some
	cases eliminating the need for Dropout. Applied to a state-of-the-art image
	classification model, Batch Normalization achieves the same accuracy with 14
	times fewer training steps, and beats the original model by a significant
	margin. Using an ensemble of batch-normalized networks, we improve upon the
	best published result on ImageNet classification: reaching 4.9% top-5
	validation error (and 4.8% test error), exceeding the accuracy of human raters.},
	added-at = {2018-07-09T15:43:42.000+0200},
	author = {Ioffe, Sergey and Szegedy, Christian},
	biburl = {https://www.bibsonomy.org/bibtex/2bd6078b46e07f6e32cc0462a28ad929b/analyst},
	description = {[1502.03167] Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift},
	interhash = {bf2b461f54850dbae02a295b9f5e799b},
	intrahash = {bd6078b46e07f6e32cc0462a28ad929b},
	keywords = {2015 arxiv deep-learning paper},
	note = {cite arxiv:1502.03167},
	timestamp = {2018-07-09T15:43:42.000+0200},
	title = {Batch Normalization: Accelerating Deep Network Training by Reducing
	Internal Covariate Shift},
	url = {http://arxiv.org/abs/1502.03167},
	year = 2015
}

@inproceedings{Guo_deepfm1,
	added-at = {2019-08-20T00:00:00.000+0200},
	author = {Guo, Huifeng and Tang, Ruiming and Ye, Yunming and Li, Zhenguo and He, Xiuqiang},
	biburl = {https://www.bibsonomy.org/bibtex/28c60cf7c56f3788385adec2feff31eb8/dblp},
	booktitle = {IJCAI},
	crossref = {conf/ijcai/2017},
	editor = {Sierra, Carles},
	ee = {https://doi.org/10.24963/ijcai.2017/239},
	interhash = {45dbc7efa61cb111c8e3e6b86fcbc1e9},
	intrahash = {8c60cf7c56f3788385adec2feff31eb8},
	isbn = {978-0-9992411-0-3},
	keywords = {dblp},
	pages = {1725-1731},
	publisher = {ijcai.org},
	timestamp = {2019-08-21T11:50:23.000+0200},
	title = {DeepFM: A Factorization-Machine based Neural Network for CTR Prediction.},
	url = {http://dblp.uni-trier.de/db/conf/ijcai/ijcai2017.html#GuoTYLH17},
	year = 2017
}

@article{Guo_deepfm2,
	added-at = {2018-08-13T00:00:00.000+0200},
	author = {Guo, Huifeng and Tang, Ruiming and Ye, Yunming and Li, Zhenguo and He, Xiuqiang and Dong, Zhenhua},
	biburl = {https://www.bibsonomy.org/bibtex/280f0da037e5fe04038cdadd5f576f2c3/dblp},
	ee = {http://arxiv.org/abs/1804.04950},
	interhash = {9bf85b0369ba8fdc3234a6ab5c0b0efe},
	intrahash = {80f0da037e5fe04038cdadd5f576f2c3},
	journal = {CoRR},
	keywords = {dblp},
	timestamp = {2018-08-14T13:49:28.000+0200},
	title = {DeepFM: An End-to-End Wide and Deep Learning Framework for CTR Prediction.},
	url = {http://dblp.uni-trier.de/db/journals/corr/corr1804.html#abs-1804-04950},
	volume = {abs/1804.04950},
	year = 2018
}

@inproceedings{Cheng_wideanddeep,
	added-at = {2018-11-06T00:00:00.000+0100},
	author = {Cheng, Heng-Tze and Koc, Levent and Harmsen, Jeremiah and Shaked, Tal and Chandra, Tushar and Aradhye, Hrishi and Anderson, Glen and Corrado, Greg and Chai, Wei and Ispir, Mustafa and Anil, Rohan and Haque, Zakaria and Hong, Lichan and Jain, Vihan and Liu, Xiaobing and Shah, Hemal},
	biburl = {https://www.bibsonomy.org/bibtex/2efca753e4be0e74da92bf8099da61ea8/dblp},
	booktitle = {DLRS@RecSys},
	crossref = {conf/recsys/2016dlrs},
	editor = {Karatzoglou, Alexandros and Hidasi, Balázs and Tikk, Domonkos and Shalom, Oren Sar and Roitman, Haggai and Shapira, Bracha and Rokach, Lior},
	ee = {https://doi.org/10.1145/2988450.2988454},
	interhash = {c8766e5f4191faa5750e5e06e508a520},
	intrahash = {efca753e4be0e74da92bf8099da61ea8},
	isbn = {978-1-4503-4795-2},
	keywords = {dblp},
	pages = {7-10},
	publisher = {ACM},
	timestamp = {2018-11-07T12:41:02.000+0100},
	title = {Wide and Deep Learning for Recommender Systems.},
	url = {http://dblp.uni-trier.de/db/conf/recsys/dlrs2016.html#Cheng0HSCAACCIA16},
	year = 2016
}

@article{Wang_asae,
	added-at = {2020-09-22T00:00:00.000+0200},
	author = {Wang, Qianqian and Liu, Fang'ai and Xing, Shuning and Zhao, Xiaohui},
	biburl = {https://www.bibsonomy.org/bibtex/25c758b41e113ef62b5ca3bab13069584/dblp},
	ee = {https://www.wikidata.org/entity/Q57300381},
	interhash = {55f89635b4315ec35f8b3f946914d866},
	intrahash = {5c758b41e113ef62b5ca3bab13069584},
	journal = {Comput. Math. Methods Medicine},
	keywords = {dblp},
	pages = {8056541:1-8056541:11},
	timestamp = {2020-09-23T11:34:11.000+0200},
	title = {A New Approach for Advertising CTR Prediction Based on Deep Neural Network via Attention Mechanism.},
	url = {http://dblp.uni-trier.de/db/journals/cmmm/cmmm2018.html#WangLXZ18},
	volume = 2018,
	year = 2018
}

@inproceedings{Ballard_autoencoder,
	added-at = {2012-12-12T00:00:00.000+0100},
	author = {Ballard, Dana H.},
	biburl = {https://www.bibsonomy.org/bibtex/23a1bf479c829398d544f4ad84e8c7657/dblp},
	booktitle = {AAAI},
	crossref = {conf/aaai/1987},
	editor = {Forbus, Kenneth D. and Shrobe, Howard E.},
	ee = {http://www.aaai.org/Library/AAAI/1987/aaai87-050.php},
	interhash = {c616c959bdfa632f6961529154757f25},
	intrahash = {3a1bf479c829398d544f4ad84e8c7657},
	keywords = {dblp},
	pages = {279-284},
	publisher = {Morgan Kaufmann},
	timestamp = {2018-06-21T11:48:19.000+0200},
	title = {Modular Learning in Neural Networks.},
	url = {http://dblp.uni-trier.de/db/conf/aaai/aaai87.html#Ballard87},
	year = 1987
}

@book{ShannonWeaver49,
	added-at = {2008-09-16T23:39:07.000+0200},
	address = {Urbana and Chicago},
	author = {Shannon, Claude E. and Weaver, Warren},
	biburl = {https://www.bibsonomy.org/bibtex/2fc189b21087056440c3194e3be26261b/brian.mingus},
	booktitle = {The Mathematical Theory of Communication},
	description = {CCNLab BibTeX},
	interhash = {ddf5810ad302fbd007f99a3b4fb0fae3},
	intrahash = {fc189b21087056440c3194e3be26261b},
	keywords = {stats},
	publisher = {University of Illinois Press},
	timestamp = {2008-09-16T23:41:10.000+0200},
	title = {The Mathematical Theory of Communication},
	year = 1949
}

@article{Naumov_embedding_dim,
	added-at = {2019-01-31T00:00:00.000+0100},
	author = {Naumov, Maxim},
	biburl = {https://www.bibsonomy.org/bibtex/2eccf1f0dfafd15cb01a6fbb1419a6735/dblp},
	ee = {http://arxiv.org/abs/1901.02103},
	interhash = {25df713996088bf05e247e8f192bb27d},
	intrahash = {eccf1f0dfafd15cb01a6fbb1419a6735},
	journal = {CoRR},
	keywords = {dblp},
	timestamp = {2019-02-01T11:37:02.000+0100},
	title = {On the Dimensionality of Embeddings for Sparse Features and Data.},
	url = {http://dblp.uni-trier.de/db/journals/corr/corr1901.html#abs-1901-02103},
	volume = {abs/1901.02103},
	year = 2019
}

@inproceedings{he2017neural,
	added-at = {2020-06-21T20:57:25.000+0200},
	address = {Republic and Canton of Geneva, CHE},
	author = {He, Xiangnan and Liao, Lizi and Zhang, Hanwang and Nie, Liqiang and Hu, Xia and Chua, Tat-Seng},
	biburl = {https://www.bibsonomy.org/bibtex/26abc7ad98fdfc7d6494a09058988c85b/sdo},
	booktitle = {Proceedings of the 26th International Conference on World Wide Web},
	doi = {10.1145/3038912.3052569},
	interhash = {500610c9f82426e50dbabe0ced94c2e9},
	intrahash = {6abc7ad98fdfc7d6494a09058988c85b},
	isbn = {9781450349130},
	keywords = {collaborative deep factorization feedback filtering implicit learning matrix networks neural},
	location = {Perth, Australia},
	numpages = {10},
	pages = {173–182},
	publisher = {International World Wide Web Conferences Steering Committee},
	series = {WWW ’17},
	timestamp = {2020-06-21T20:57:25.000+0200},
	title = {Neural Collaborative Filtering},
	url = {https://doi.org/10.1145/3038912.3052569},
	year = 2017
}

@inproceedings{maas2013leakyrelu,
	title={Rectifier nonlinearities improve neural network acoustic models},
	author={Maas, Andrew L and Hannun, Awni Y and Ng, Andrew Y},
	booktitle={Proc. icml},
	volume={30},
	number={1},
	pages={3},
	year={2013},
	organization={Citeseer}
}

@article{t-sne,
	added-at = {2017-01-24T11:10:59.000+0100},
	author = {van der Maaten, Laurens and Hinton, Geoffrey},
	biburl = {https://www.bibsonomy.org/bibtex/28b9aebb404ad4a4c6a436ea413550b30/nosebrain},
	interhash = {370ba8b9e1909b61880a6f47c93bcd49},
	intrahash = {8b9aebb404ad4a4c6a436ea413550b30},
	journal = {Journal of Machine Learning Research},
	keywords = {data t-sne visualization},
	pages = {2579--2605},
	timestamp = {2017-01-24T11:10:59.000+0100},
	title = {Visualizing Data using {t-SNE} },
	url = {http://www.jmlr.org/papers/v9/vandermaaten08a.html},
	volume = 9,
	year = 2008
}

@article{Ginart_MixedDimEmb,
	added-at = {2019-09-27T00:00:00.000+0200},
	author = {Ginart, Antonio and Naumov, Maxim and Mudigere, Dheevatsa and Yang, Jiyan and Zou, James},
	biburl = {https://www.bibsonomy.org/bibtex/2c5035c95f2b669264227e6d5ce35497a/dblp},
	ee = {http://arxiv.org/abs/1909.11810},
	interhash = {a2574b7523b570e6928cd2d28506206b},
	intrahash = {c5035c95f2b669264227e6d5ce35497a},
	journal = {CoRR},
	keywords = {dblp},
	timestamp = {2019-09-28T11:37:55.000+0200},
	title = {Mixed Dimension Embeddings with Application to Memory-Efficient Recommendation Systems.},
	url = {http://dblp.uni-trier.de/db/journals/corr/corr1909.html#abs-1909-11810},
	volume = {abs/1909.11810},
	year = 2019
}


@article{choi2020online,
	added-at = {2020-07-31T00:00:00.000+0200},
	author = {Choi, Hana and Mela, Carl F. and Balseiro, Santiago R. and Leary, Adam},
	biburl = {https://www.bibsonomy.org/bibtex/22abdd5a8fcbecc6f6c6dcff05bd30dd8/dblp},
	ee = {https://doi.org/10.1287/isre.2019.0902},
	interhash = {4449e1306bf6c274e9d57342192c0bc8},
	intrahash = {2abdd5a8fcbecc6f6c6dcff05bd30dd8},
	journal = {Inf. Syst. Res.},
	keywords = {dblp},
	number = 2,
	pages = {556-575},
	timestamp = {2020-08-01T11:38:28.000+0200},
	title = {Online Display Advertising Markets: A Literature Review and Future Directions.},
	url = {http://dblp.uni-trier.de/db/journals/isr/isr31.html#ChoiMBL20},
	volume = 31,
	year = 2020
}

@INPROCEEDINGS{yuan2014survey,  author={Yuan, Yong and Wang, Feiyue and Li, Juanjuan and Qin, Rui},  booktitle={Proceedings of 2014 IEEE International Conference on Service Operations and Logistics, and Informatics},   title={A survey on real time bidding advertising},   year={2014},  volume={},  number={},  pages={418-423},  doi={10.1109/SOLI.2014.6960761}}

@inproceedings{qin2019revenue,
	added-at = {2019-10-18T00:00:00.000+0200},
	author = {Qin, Rui and Ni, Xiaochun and Yuan, Yong and Li, Juanjuan and Wang, Fei-Yue},
	biburl = {https://www.bibsonomy.org/bibtex/24e703bb84e53b4b34f5168c32d365ddf/dblp},
	booktitle = {SMC},
	crossref = {conf/smc/2017},
	ee = {https://doi.org/10.1109/SMC.2017.8122644},
	interhash = {b57212f4c4a7349707a060f9b3005db9},
	intrahash = {4e703bb84e53b4b34f5168c32d365ddf},
	isbn = {978-1-5386-1645-1},
	keywords = {dblp},
	pages = {438-443},
	publisher = {IEEE},
	timestamp = {2019-10-19T11:40:41.000+0200},
	title = {Revenue models for demand side platforms in real time bidding advertising.},
	url = {http://dblp.uni-trier.de/db/conf/smc/smc2017.html#QinNYLW17},
	year = 2017
}

@incollection{reference/ml/LingS17,
	added-at = {2017-04-18T00:00:00.000+0200},
	author = {Ling, Charles X. and Sheng, Victor S.},
	biburl = {https://www.bibsonomy.org/bibtex/244fcb6ab821f14b0318d4f1c26db9723/dblp},
	booktitle = {Encyclopedia of Machine Learning and Data Mining},
	crossref = {reference/ml/2017},
	editor = {Sammut, Claude and Webb, Geoffrey I.},
	ee = {http://dx.doi.org/10.1007/978-1-4899-7687-1_110},
	interhash = {e976e365819bfb5007ab4e447b8db77c},
	intrahash = {44fcb6ab821f14b0318d4f1c26db9723},
	isbn = {978-1-4899-7687-1},
	keywords = {dblp},
	pages = {204-205},
	publisher = {Springer},
	timestamp = {2017-04-19T11:47:40.000+0200},
	title = {Class Imbalance Problem.},
	url = {http://dblp.uni-trier.de/db/reference/ml/ml2017.html#LingS17},
	year = 2017
}


@misc{pires2019high,
	title={High dimensionality: The latest challenge to data analysis}, 
	author={A. M. Pires and J. A. Branco},
	year={2019},
	eprint={1902.04679},
	archivePrefix={arXiv},
	primaryClass={stat.ME}
}

@article{journals/eswa/LikaKH14,
	added-at = {2018-11-14T00:00:00.000+0100},
	author = {Lika, Blerina and Kolomvatsos, Kostas and Hadjiefthymiades, Stathes},
	biburl = {https://www.bibsonomy.org/bibtex/2fc178a46831b1274c383c7f59a6e45a1/dblp},
	ee = {https://www.wikidata.org/entity/Q56699601},
	interhash = {75c03e661d776a34045e2aa7f6f25623},
	intrahash = {fc178a46831b1274c383c7f59a6e45a1},
	journal = {Expert Syst. Appl.},
	keywords = {dblp},
	number = 4,
	pages = {2065-2073},
	timestamp = {2018-11-15T12:09:50.000+0100},
	title = {Facing the cold start problem in recommender systems.},
	url = {http://dblp.uni-trier.de/db/journals/eswa/eswa41.html#LikaKH14},
	volume = 41,
	year = 2014
}

@article{DBLP:journals/corr/abs-1004-3732,
	author    = {Zi{-}Ke Zhang and
	Chuang Liu and
	Yi{-}Cheng Zhang and
	Tao Zhou},
	title     = {Solving the Cold-Start Problem in Recommender Systems with Social
	Tags},
	journal   = {CoRR},
	volume    = {abs/1004.3732},
	year      = {2010},
	url       = {http://arxiv.org/abs/1004.3732},
	archivePrefix = {arXiv},
	eprint    = {1004.3732},
	timestamp = {Mon, 13 Aug 2018 16:46:35 +0200},
	biburl    = {https://dblp.org/rec/journals/corr/abs-1004-3732.bib},
	bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{journals/corr/ZhangYS17aa,
	added-at = {2018-11-19T00:00:00.000+0100},
	author = {Zhang, Shuai and Yao, Lina and Sun, Aixin},
	biburl = {https://www.bibsonomy.org/bibtex/24638a74008191211151c5f5b989deaf6/dblp},
	ee = {http://arxiv.org/abs/1707.07435},
	interhash = {b9deeb062ab460de31016200e0fe712d},
	intrahash = {4638a74008191211151c5f5b989deaf6},
	journal = {CoRR},
	keywords = {dblp},
	timestamp = {2018-11-20T11:37:21.000+0100},
	title = {Deep Learning based Recommender System: A Survey and New Perspectives.},
	url = {http://dblp.uni-trier.de/db/journals/corr/corr1707.html#ZhangYS17aa},
	volume = {abs/1707.07435},
	year = 2017
}