{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:41:24Z","timestamp":1772120484957,"version":"3.50.1"},"reference-count":70,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2020,11,23]],"date-time":"2020-11-23T00:00:00Z","timestamp":1606089600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,11,23]],"date-time":"2020-11-23T00:00:00Z","timestamp":1606089600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Swiss Federal Institute of Technology Zurich"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2021,2]]},"abstract":"Abstract<\/jats:title>When training a deep neural network for image classification, one can broadly distinguish between two types of latent features of images that will drive the classification. We can divide latent features into (i) \u2018core\u2019 or \u2018conditionally invariant\u2019 features$$C$$<\/jats:tex-math>C<\/mml:mi><\/mml:math><\/jats:alternatives><\/jats:inline-formula>whose distribution$$C\\vert Y$$<\/jats:tex-math>C<\/mml:mi>|<\/mml:mo>Y<\/mml:mi><\/mml:mrow><\/mml:math><\/jats:alternatives><\/jats:inline-formula>, conditional on the classY<\/jats:italic>, does not change substantially across domains and (ii) \u2018style\u2019 features$$S$$<\/jats:tex-math>S<\/mml:mi><\/mml:math><\/jats:alternatives><\/jats:inline-formula>whose distribution$$S\\vert Y$$<\/jats:tex-math>S<\/mml:mi>|<\/mml:mo>Y<\/mml:mi><\/mml:mrow><\/mml:math><\/jats:alternatives><\/jats:inline-formula>can change substantially across domains. Examples for style features include position, rotation, image quality or brightness but also more complex ones like hair color, image quality or posture for images of persons. Our goal is to minimize a loss that is robust under changes in the distribution of these style features. In contrast to previous work, we assume that the domain itself is not observed and hence a latent variable. We do assume that we can sometimes observe a typically discrete identifier or \u201c$$\\mathrm {ID}$$<\/jats:tex-math>ID<\/mml:mi><\/mml:math><\/jats:alternatives><\/jats:inline-formula>variable\u201d. In some applications we know, for example, that two images show the same person, and$$\\mathrm {ID}$$<\/jats:tex-math>ID<\/mml:mi><\/mml:math><\/jats:alternatives><\/jats:inline-formula>then refers to the identity of the person. The proposed method requires only a small fraction of images to have$$\\mathrm {ID}$$<\/jats:tex-math>ID<\/mml:mi><\/mml:math><\/jats:alternatives><\/jats:inline-formula>information. We group observations if they share the same class and identifier$$(Y,\\mathrm {ID})=(y,\\mathrm {id})$$<\/jats:tex-math>(<\/mml:mo>Y<\/mml:mi>,<\/mml:mo>ID<\/mml:mi>)<\/mml:mo>=<\/mml:mo>(<\/mml:mo>y<\/mml:mi>,<\/mml:mo>id<\/mml:mi>)<\/mml:mo><\/mml:mrow><\/mml:math><\/jats:alternatives><\/jats:inline-formula>and penalize the conditional variance of the prediction or the loss if we condition on$$(Y,\\mathrm {ID})$$<\/jats:tex-math>(<\/mml:mo>Y<\/mml:mi>,<\/mml:mo>ID<\/mml:mi>)<\/mml:mo><\/mml:mrow><\/mml:math><\/jats:alternatives><\/jats:inline-formula>. Using a causal framework, this conditional variance regularization (Co<\/jats:sc>Re<\/jats:sc>) is shown to protect asymptotically against shifts in the distribution of the style variables in a partially linear structural equation model. Empirically, we show that the Co<\/jats:sc>Re<\/jats:sc>penalty improves predictive accuracy substantially in settings where domain changes occur in terms of image quality, brightness and color while we also look at more complex changes such as changes in movement and posture.<\/jats:p>","DOI":"10.1007\/s10994-020-05924-1","type":"journal-article","created":{"date-parts":[[2020,11,23]],"date-time":"2020-11-23T22:03:01Z","timestamp":1606168981000},"page":"303-348","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":37,"title":["Conditional variance penalties and domain shift robustness"],"prefix":"10.1007","volume":"110","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2489-9415","authenticated-orcid":false,"given":"Christina","family":"Heinze-Deml","sequence":"first","affiliation":[]},{"given":"Nicolai","family":"Meinshausen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,23]]},"reference":[{"key":"5924_CR1","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jia, Y., Jozefowicz, R., Kaiser, L., Kudlur, M., Levenberg, J., Man\u00e9, D., Monga, R., Moore, S., Murray, D., Olah, C., Schuster, M., Shlens, J., Steiner, B., Sutskever, I., Talwar, K., Tucker, P., Vanhoucke, V., Vasudevan, V., Vi\u00e9gas, F., Vinyals, O., Warden, P., Wattenberg, M., Wicke, M., Yu, Y., & Zheng, X. (2015). TensorFlow: Large-scale machinelearning on heterogeneous systems.https:\/\/www.tensorflow.org\/, software available fromtensorflow.org."},{"key":"5924_CR2","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1093\/oxfordjournals.oep.a041889","volume":"41","author":"J Aldrich","year":"1989","unstructured":"Aldrich, J. (1989). Autonomy. Oxford Economic Papers, 41, 15\u201334.","journal-title":"Oxford Economic Papers"},{"key":"5924_CR3","unstructured":"Bagnell, J. (2005). Robust supervised learning. In Proceedings of the national conference on artificial intelligence, Menlo Park, CA; Cambridge, MA; London; AAAI Press; MIT Press; (1999) Vol.\u00a020, p. 714."},{"key":"5924_CR4","unstructured":"Bahadori, M. T., Chalupka, K., Choi, E., Chen, R., Stewart, W. F., & Sun, J. (2017). Causal regularization. arXiv:170202604."},{"key":"5924_CR5","doi-asserted-by":"crossref","unstructured":"Barocas, S., & Selbst, A.D. (2016). Big Data\u2019s Disparate Impact. 104 California Law Review 671.","DOI":"10.2139\/ssrn.2477899"},{"key":"5924_CR6","unstructured":"Bartlett, M.S., Sejnowski, T. J. (1996). Viewpoint invariant face recognition using independent component analysis and attractor networks. In Proceedings of the 9th International Conference on Neural Information Processing Systems (pp. 817\u2013823), MIT Press, Cambridge, MA, USA, NIPS\u201996."},{"issue":"Nov","key":"5924_CR7","first-page":"2399","volume":"7","author":"M Belkin","year":"2006","unstructured":"Belkin, M., Niyogi, P., & Sindhwani, V. (2006). Manifold regularization: A geometric framework for learning from labeled and unlabeled examples. Journal of Machine Learning Research, 7(Nov), 2399\u20132434.","journal-title":"Journal of Machine Learning Research"},{"key":"5924_CR8","doi-asserted-by":"crossref","unstructured":"Ben-David, S., Blitzer, J., Crammer, K., & Pereira, F. (2007). Analysis of representations for domain adaptation. In Advances in Neural Information Processing Systems, Vol. 19.","DOI":"10.7551\/mitpress\/7503.003.0022"},{"issue":"2","key":"5924_CR9","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1287\/mnsc.1120.1641","volume":"59","author":"A Ben-Tal","year":"2013","unstructured":"Ben-Tal, A., Den Hertog, D., De Waegenaere, A., Melenberg, B., & Rennen, G. (2013). Robust solutions of optimization problems affected by uncertain probabilities. Management Science, 59(2), 341\u2013357.","journal-title":"Management Science"},{"key":"5924_CR10","unstructured":"Besserve, M., Shajarisales, N., Sch\u00f6lkopf, B., & Janzing, D. (2018). Group invariance principles for causal generative models. In Proceedings of the 21st International Conference on Artificial Intelligence and Statistics (AISTATS), PMLR, Proceedings of Machine Learning Research (pp. 557\u2013565), Vol.\u00a084."},{"key":"5924_CR11","unstructured":"Bolukbasi, T., Chang, K. W., Zou, J. Y., Saligrama, V., & Kalai, A. T. (2016). Man is to computer programmer as woman is to homemaker? Debiasing word embeddings. In Advances in Neural Information Processing Systems, Vol. 29."},{"key":"5924_CR12","doi-asserted-by":"crossref","unstructured":"Bouchacourt, D., Tomioka, R., & Nowozin, S. (2018). Multi-level variational autoencoder: Learning disentangled representations from grouped observations. In AAAI Conference on Artificial Intelligence.","DOI":"10.1609\/aaai.v32i1.11867"},{"key":"5924_CR13","unstructured":"Chalupka, K., Perona, P., & Eberhardt, F. (2014). Visual Causal Feature Learning. Uncertainty in Artificial Intelligence."},{"key":"5924_CR14","unstructured":"Crawford, K. (2016). Artificial intelligence\u2019s white guy problem. The New York Times, June 25 2016 https:\/\/www.nytimes.com\/2016\/06\/26\/opinion\/sunday\/artificial-intelligences-white-guy-problem.html."},{"key":"5924_CR15","doi-asserted-by":"crossref","unstructured":"Csurka, G. (2017). A comprehensive survey on domain adaptation for visual applications. In Domain Adaptation in Computer Vision Applications (pp. 1\u201335).","DOI":"10.1007\/978-3-319-58347-1_1"},{"key":"5924_CR16","unstructured":"Denton, E. L., & Birodkar, V. (2017). Unsupervised learning of disentangled representations from video. In Advances in Neural Information Processing Systems, Vol. 30."},{"key":"5924_CR17","unstructured":"Devries, T., & Taylor, G. W. (2017). Dataset augmentation in feature space. ICLR Workshop Track."},{"key":"5924_CR18","unstructured":"Emspak, J. (2016). How a machine learns prejudice. Scientific American, December 29 2016 https:\/\/www.scientificamerican.com\/article\/how-a-machine-learns-prejudice\/."},{"key":"5924_CR19","unstructured":"Engstrom, L., Ilyas, A., & Athalye, A. (2018). Evaluating and understanding the robustness of adversarial logit pairing. arXiv:180710272."},{"issue":"1","key":"5924_CR20","first-page":"2096","volume":"17","author":"Y Ganin","year":"2016","unstructured":"Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., et al. (2016). Domain-adversarial training of neural networks. Journal of Machine Learning Research, 17(1), 2096\u20132030.","journal-title":"Journal of Machine Learning Research"},{"key":"5924_CR21","unstructured":"Gao, R., Chen, X., & Kleywegt, A. (2017). arXiv:171206050."},{"key":"5924_CR22","unstructured":"Gong, B., Grauman, K., & Sha, F. (2013). Reshaping visual datasets for domain adaptation. In Advances in Neural Information Processing Systems (Vol. 26, pp. 1286\u20131294), Curran Associates, Inc."},{"key":"5924_CR23","unstructured":"Gong, M., Zhang, K., Liu, T., Tao, D., Glymour, C., & Sch\u00f6lkopf, B. (2016). Domain adaptation with conditional transferable components. In International Conference on Machine Learning."},{"key":"5924_CR24","unstructured":"Goodfellow, I., Shlens, J., & Szegedy C. (2015). Explaining and harnessing adversarial examples. In International conference on learning representations."},{"key":"5924_CR25","unstructured":"Goudet, O., Kalainathan, D., Caillou, P., Lopez-Paz, D., Guyon, I., Sebag, M., Tritas, A., & Tubaro, P. (2017). Learning functional causal models with generative neural networks. arXiv:170905321."},{"key":"5924_CR26","unstructured":"Haavelmo, T. (1944). The probability approach in econometrics. Econometrica 12:S1\u2013S115 (supplement)."},{"key":"5924_CR27","unstructured":"Hashimoto, T. B., Liang, P. S., & Duchi, J. C. (2017). Unsupervised transformation learning via convex relaxations. In Advances in neural information processing systems (Vol. 30, pp. 6875\u20136883), Curran Associates, Inc."},{"key":"5924_CR28","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2015). Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In Proceedings of the 2015 IEEE international conference on computer vision (ICCV) (pp. 1026\u20131034).","DOI":"10.1109\/ICCV.2015.123"},{"key":"5924_CR29","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In 2016 IEEE conference on computer vision and pattern recognition (CVPR) (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"5924_CR30","unstructured":"Hoffman, J., Kulis, B., Darrell, T., & Saenko, K. (2012). Discovering latent domains for multisource domain adaptation. In Computer Vision - ECCV 2012 (pp. 702\u2013715). Berlin Heidelberg, Berlin, Heidelberg: Springer."},{"key":"5924_CR31","unstructured":"Kannan, H., Kurakin, A., & Goodfellow, I. J. (2018). Adversarial logit pairing. arXiv:180306373."},{"key":"5924_CR32","unstructured":"Khasanova, R., & Frossard, P. (2017). Graph-based isometry invariant representation learning. In Proceedings of the 34th international conference on machine learning (Vol.\u00a070, pp. 1847\u20131856)."},{"key":"5924_CR33","first-page":"656","volume":"30","author":"N Kilbertus","year":"2017","unstructured":"Kilbertus, N., Rojas Carulla, M., Parascandolo, G., Hardt, M., Janzing, D., & Sch\u00f6lkopf, B. (2017). Avoiding discrimination through causal reasoning. Advances in Neural Information Processing Systems, 30, 656\u2013666.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"5924_CR34","unstructured":"Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. International Conference on Learning Representations (ICLR)."},{"key":"5924_CR35","unstructured":"Kocaoglu, M., Snyder, C., Dimakis, A., & Vishwanath, S. (2018). CausalGAN: Learning causal implicit generative models with adversarial training. In International conference on learning representations."},{"key":"5924_CR36","unstructured":"Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems, Vol. 25."},{"key":"5924_CR37","doi-asserted-by":"crossref","unstructured":"Kuehlkamp, A., Becker, B., & Bowyer, K. (2017). Gender-from-iris or gender-from-mascara? In 2017 IEEE winter conference on applications of computer vision (WACV).","DOI":"10.1109\/WACV.2017.133"},{"key":"5924_CR38","doi-asserted-by":"crossref","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE.","DOI":"10.1109\/5.726791"},{"issue":"414","key":"5924_CR39","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1080\/01621459.1991.10475035","volume":"86","author":"KC Li","year":"1991","unstructured":"Li, K. C. (1991). Sliced inverse regression for dimension reduction. Journal of the American Statistical Association, 86(414), 316\u2013327.","journal-title":"Journal of the American Statistical Association"},{"key":"5924_CR40","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Wang, X., & Tang, X. (2015). Deep learning face attributes in the wild. In Proceedings of International Conference on Computer Vision (ICCV).","DOI":"10.1109\/ICCV.2015.425"},{"key":"5924_CR41","unstructured":"Lopez-Paz, D., & Oquab, M. (2017). Revisiting classifier two-sample tests. In International conference on learning representations (ICLR)."},{"key":"5924_CR42","doi-asserted-by":"crossref","unstructured":"Lopez-Paz, D., Nishihara, R., Chintala, S., Sch\u00f6lkopf, B., & Bottou, L. (2017). Discovering causal signals in images. In The IEEE conference on computer vision and pattern recognition (CVPR 2017).","DOI":"10.1109\/CVPR.2017.14"},{"key":"5924_CR43","unstructured":"Magliacane, S., van Ommen, T., Claassen, T., Bongers, S., Versteeg, P., & Mooij, J. (2018). Domain adaptation by using causal inference to predict invariant conditional distributions. In Advances in neural information processing systems."},{"key":"5924_CR44","doi-asserted-by":"crossref","unstructured":"Meinshausen, N. (2018). Causality from a distributional robustness point of view. In 2018 IEEE Data Science Workshop (DSW) (pp. 6\u201310).","DOI":"10.1109\/DSW.2018.8439889"},{"key":"5924_CR45","unstructured":"Mosbach, M., Andriushchenko, M., Trost, T., Hein, M., & Klakow, D. (2018). Logit pairing methods can fool gradient-based attacks. arXiv:181012042."},{"key":"5924_CR46","unstructured":"Namkoong, H., & Duchi, J. (2017). Variance-based regularization with convex objectives. In Advances in Neural Information Processing Systems (pp. 2975\u20132984)."},{"key":"5924_CR47","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511803161","volume-title":"Causality: Models, reasoning, and inference","author":"J Pearl","year":"2009","unstructured":"Pearl, J. (2009). Causality: Models, reasoning, and inference (2nd ed.). New York: Cambridge University Press.","edition":"2"},{"key":"5924_CR48","doi-asserted-by":"publisher","first-page":"947","DOI":"10.1111\/rssb.12167","volume":"78","author":"J Peters","year":"2016","unstructured":"Peters, J., B\u00fchlmann, P., & Meinshausen, N. (2016). Causal inference using invariant prediction: identification and confidence intervals. Journal of the Royal Statistical Society, Series B, 78, 947\u20131012.","journal-title":"Journal of the Royal Statistical Society, Series B"},{"key":"5924_CR49","volume-title":"Dataset shift in machine learning","author":"J Quionero-Candela","year":"2009","unstructured":"Quionero-Candela, J., Sugiyama, M., Schwaighofer, A., & Lawrence, N. D. (2009). Dataset shift in machine learning. Cambridge: The MIT Press."},{"key":"5924_CR50","unstructured":"Richardson, T., & Robins, J. M. (2013). Single world intervention graphs (SWIGs): A unification of the counterfactual and graphical approaches to causality. Center for the Statistics and the Social Sciences, University of Washington Series Working Paper 128, 30 April 2013."},{"key":"5924_CR51","unstructured":"Rojas-Carulla, M., Sch\u00f6lkopf, B., Turner, R., & Peters, J. (2018). Causal transfer in machine learning. To appear in Journal of Machine Learning Research."},{"key":"5924_CR52","unstructured":"Rothenh\u00e4usler, D., B\u00fchlmann, P., Meinshausen, N., & Peters, J. (2018). Anchor regression: heterogeneous data meets causality. arXiv:180106229."},{"key":"5924_CR53","unstructured":"Sch\u00f6lkopf, B., Burges, C., & Vapnik, V. (1996). Incorporating invariances in support vector learning machines. Artificial Neural Networks \u2013 ICANN 96 (pp. 47\u201352). Berlin Heidelberg, Berlin, Heidelberg: Springer."},{"key":"5924_CR54","unstructured":"Sch\u00f6lkopf, B., Janzing, D., Peters, J., Sgouritsa, E., Zhang, K., & Mooij, J. (2012). On causal and anticausal learning. In Proceedings of the 29th international conference on machine learning (ICML) (pp. 1255\u20131262)."},{"key":"5924_CR55","unstructured":"Shafieezadeh-Abadeh, S., Kuhn, D., & Esfahani, P. (2017). Regularization via mass transportation. arXiv:171010016."},{"key":"5924_CR56","unstructured":"Sinha, A., Namkoong, H., & Duchi, J. (2018). Certifiable distributional robustness with principled adversarial training. In International conference on learning representations."},{"key":"5924_CR57","unstructured":"Sohn, K., & Lee, H. (2012). Learning invariant representations with local transformations. In Proceedings of the 29th international coference on international conference on machine learning, Omnipress, USA, ICML\u201912, pp. 1339\u20131346."},{"key":"5924_CR58","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015). Going deeper with convolutions. In Computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"5924_CR59","unstructured":"Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., & Fergus, R. (2014). Intriguing properties of neural networks. In International conference on learning representations."},{"key":"5924_CR60","doi-asserted-by":"crossref","unstructured":"Torralba, A., & Efros, A. A. (2011). Unbiased look at dataset bias. In Computer Vision and Pattern Recognition (CVPR).","DOI":"10.1109\/CVPR.2011.5995347"},{"key":"5924_CR61","doi-asserted-by":"crossref","unstructured":"Tran, L., Yin, X., & Liu, X. (2017). Disentangled representation learning gan for pose-invariant face recognition. In Proceeding of IEEE computer vision and pattern recognition, Honolulu, HI","DOI":"10.1109\/CVPR.2017.141"},{"key":"5924_CR62","doi-asserted-by":"crossref","unstructured":"Venkateswara, H., Eusebio, J., Chakraborty, S., & Panchanathan, S. (2017). Deep hashing network for unsupervised domain adaptation. In (IEEE) Conference on Computer Vision and Pattern Recognition (CVPR).","DOI":"10.1109\/CVPR.2017.572"},{"key":"5924_CR63","volume-title":"Topics in optimal transportation","author":"C Villani","year":"2003","unstructured":"Villani, C. (2003). Topics in optimal transportation (Vol. 58). Providence: American Mathematical Society."},{"key":"5924_CR64","unstructured":"Volpi, R., Namkoong, H., Sener, O., Duchi, J., Murino, V., & Savarese, S. (2018). Generalizing to unseen domains via adversarial data augmentation. arXiv:180512018."},{"key":"5924_CR65","unstructured":"Xian, Y., Lampert, C. H., Schiele, B., & Akata, Z. (2017). Zero-shot learning\u2014A comprehensive evaluation of the good, the bad and the ugly. arXiv:170700600."},{"key":"5924_CR66","unstructured":"Xu, H., Caramanis, C., & Mannor, S. (2009). Robust regression and lasso. In Advances in Neural Information Processing Systems (pp. 1801\u20131808)."},{"key":"5924_CR67","unstructured":"Xu, C., Tao, D., & Xu, C. (2013). A survey on multi-view learning. arXiv:13045634."},{"key":"5924_CR68","unstructured":"Yu, X., Liu, T., Gong, M., Zhang, K., & Tao, D. (2017). Transfer learning with label noise. arXiv:170709724."},{"key":"5924_CR69","doi-asserted-by":"crossref","unstructured":"Zhang, K., Gong, M., & Sch\u00f6lkopf, B. (2015). Multi-source domain adaptation: A causal view. In Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence.","DOI":"10.1609\/aaai.v29i1.9542"},{"key":"5924_CR70","unstructured":"Zhang, K., Sch\u00f6lkopf, B., Muandet, K., & Wang, Z. (2013). Domain adaptation under target and conditional shift. In International Conference on Machine Learning."}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-020-05924-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10994-020-05924-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-020-05924-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,13]],"date-time":"2023-10-13T12:54:54Z","timestamp":1697201694000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10994-020-05924-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,23]]},"references-count":70,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2021,2]]}},"alternative-id":["5924"],"URL":"https:\/\/doi.org\/10.1007\/s10994-020-05924-1","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,11,23]]},"assertion":[{"value":"15 July 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 October 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 October 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 November 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}