{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:57:27Z","timestamp":1772121447917,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,8,4]],"date-time":"2023-08-04T00:00:00Z","timestamp":1691107200000},"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":[[2023,8,6]]},"DOI":"10.1145\/3580305.3599877","type":"proceedings-article","created":{"date-parts":[[2023,8,4]],"date-time":"2023-08-04T18:10:58Z","timestamp":1691172658000},"page":"4219-4228","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Off-Policy Learning-to-Bid with AuctionGym"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6256-5814","authenticated-orcid":false,"given":"Olivier","family":"Jeunen","sequence":"first","affiliation":[{"name":"ShareChat, Edinburgh, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4539-8433","authenticated-orcid":false,"given":"Sean","family":"Murphy","sequence":"additional","affiliation":[{"name":"Amazon, Edinburgh, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9073-1626","authenticated-orcid":false,"given":"Ben","family":"Allison","sequence":"additional","affiliation":[{"name":"Amazon, Edinburgh, United Kingdom"}]}],"member":"320","published-online":{"date-parts":[[2023,8,4]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"P. Bajari B. Burdick G. W. Imbens L. Masoero J. McQueen T. Richardson and I. M. Rosen. 2021. Multiple Randomization Designs. https:\/\/arxiv.org\/abs\/2112.13495  P. Bajari B. Burdick G. W. Imbens L. Masoero J. McQueen T. Richardson and I. M. Rosen. 2021. Multiple Randomization Designs. https:\/\/arxiv.org\/abs\/2112.13495"},{"key":"e_1_3_2_2_2_1","volume-title":"Carousel Personalization in Music Streaming Apps with Contextual Bandits. In RecSys '20","author":"Bendada W.","unstructured":"W. Bendada , G. Salha , and T. Bontempelli . 2020 . Carousel Personalization in Music Streaming Apps with Contextual Bandits. In RecSys '20 . W. Bendada, G. Salha, and T. Bontempelli. 2020. Carousel Personalization in Music Streaming Apps with Contextual Bandits. In RecSys '20."},{"key":"e_1_3_2_2_3_1","unstructured":"G. Brockman V. Cheung L. Pettersson J. Schneider J. Schulman J. Tang and W. Zaremba. 2016. OpenAI Gym. https:\/\/arxiv.org\/abs\/1606.01540  G. Brockman V. Cheung L. Pettersson J. Schneider J. Schulman J. Tang and W. Zaremba. 2016. OpenAI Gym. https:\/\/arxiv.org\/abs\/1606.01540"},{"key":"e_1_3_2_2_4_1","volume-title":"An Empirical Evaluation of Thompson Sampling. In NeurIPS '11","author":"Chapelle O.","unstructured":"O. Chapelle and L. Li . 2011 . An Empirical Evaluation of Thompson Sampling. In NeurIPS '11 . O. Chapelle and L. Li. 2011. An Empirical Evaluation of Thompson Sampling. In NeurIPS '11."},{"key":"e_1_3_2_2_5_1","volume-title":"Doubly Robust Policy Evaluation and Learning. In ICML '11","author":"Dud\u00edk M.","unstructured":"M. Dud\u00edk , J. Langford , and L. Li . 2011 . Doubly Robust Policy Evaluation and Learning. In ICML '11 . M. Dud\u00edk, J. Langford, and L. Li. 2011. Doubly Robust Policy Evaluation and Learning. In ICML '11."},{"key":"e_1_3_2_2_6_1","volume-title":"ICML '19","author":"Duetting P.","unstructured":"P. Duetting , Z. Feng , H. Narasimhan , D. Parkes , and S. S. Ravindranath . 2019. Optimal Auctions through Deep Learning . In ICML '19 . P. Duetting, Z. Feng, H. Narasimhan, D. Parkes, and S. S. Ravindranath. 2019. Optimal Auctions through Deep Learning. In ICML '19."},{"key":"e_1_3_2_2_7_1","volume-title":"SimuRec: Workshop on Synthetic Data and Simulation Methods for Recommender Systems Research. In RecSys '21","author":"Ekstrand M. D.","unstructured":"M. D. Ekstrand , A. Chaney , P. Castells , R. Burke , D. Rohde , and M. Slokom . 2021 . SimuRec: Workshop on Synthetic Data and Simulation Methods for Recommender Systems Research. In RecSys '21 . M. D. Ekstrand, A. Chaney, P. Castells, R. Burke, D. Rohde, and M. Slokom. 2021. SimuRec: Workshop on Synthetic Data and Simulation Methods for Recommender Systems Research. In RecSys '21."},{"key":"e_1_3_2_2_8_1","volume-title":"More Robust Doubly Robust Off-policy Evaluation. In ICML '19","author":"Farajtabar M.","unstructured":"M. Farajtabar , Y. Chow , and M. Ghavamzadeh . 2018 . More Robust Doubly Robust Off-policy Evaluation. In ICML '19 . M. Farajtabar, Y. Chow, and M. Ghavamzadeh. 2018. More Robust Doubly Robust Off-policy Evaluation. In ICML '19."},{"key":"e_1_3_2_2_9_1","volume-title":"Distributionally Robust Counterfactual Risk Minimization. In AAAI '20","author":"Faury L.","unstructured":"L. Faury , U. Tanielian , F. Vasile , E. Smirnova , and E. Dohmatob . 2020 . Distributionally Robust Counterfactual Risk Minimization. In AAAI '20 . L. Faury, U. Tanielian, F. Vasile, E. Smirnova, and E. Dohmatob. 2020. Distributionally Robust Counterfactual Risk Minimization. In AAAI '20."},{"key":"e_1_3_2_2_10_1","volume-title":"WSDM '19","author":"Gilotte A.","unstructured":"A. Gilotte , C. Calauz\u00e8nes , T. Nedelec , A. Abraham , and S. Doll\u00e9 . 2018. Offline A\/B Testing for Recommender Systems . In WSDM '19 . A. Gilotte, C. Calauz\u00e8nes, T. Nedelec, A. Abraham, and S. Doll\u00e9. 2018. Offline A\/B Testing for Recommender Systems. In WSDM '19."},{"key":"e_1_3_2_2_11_1","volume-title":"Bid Shading in The Brave New World of First-Price Auctions. In CIKM '20","author":"Gligorijevic D.","unstructured":"D. Gligorijevic , T. Zhou , B. Shetty , B. Kitts , S. Pan , J. Pan , and A. Flores . 2020 . Bid Shading in The Brave New World of First-Price Auctions. In CIKM '20 . D. Gligorijevic, T. Zhou, B. Shetty, B. Kitts, S. Pan, J. Pan, and A. Flores. 2020. Bid Shading in The Brave New World of First-Price Auctions. In CIKM '20."},{"key":"e_1_3_2_2_12_1","volume-title":"Problems of Monetary Management: The UK Experience","author":"Goodhart C. A. E.","unstructured":"C. A. E. Goodhart . 1984. Problems of Monetary Management: The UK Experience . Macmillan Education UK , 91--121. C. A. E. Goodhart. 1984. Problems of Monetary Management: The UK Experience. Macmillan Education UK, 91--121."},{"key":"e_1_3_2_2_13_1","volume-title":"ICML '19","author":"Haarnoja T.","unstructured":"T. Haarnoja , A. Zhou , P. Abbeel , and S. Levine . 2018. Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor . In ICML '19 . T. Haarnoja, A. Zhou, P. Abbeel, and S. Levine. 2018. Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor. In ICML '19."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"crossref","unstructured":"C. R. Harris K. J. Millman S. J. van der Walt R. Gommers P. Virtanen D. Cournapeau E. Wieser J. Taylor S. Berg N. J. Smith R. Kern M. Picus S. Hoyer M. H. van Kerkwijk M. Brett A. Haldane J. F. del R\u00edo M. Wiebe P. Peterson P. G\u00e9rard-Marchant K. Sheppard T. Reddy W. Weckesser H. Abbasi C. G. and T. E. Oliphant. 2020. Array programming with NumPy. Nature (2020).  C. R. Harris K. J. Millman S. J. van der Walt R. Gommers P. Virtanen D. Cournapeau E. Wieser J. Taylor S. Berg N. J. Smith R. Kern M. Picus S. Hoyer M. H. van Kerkwijk M. Brett A. Haldane J. F. del R\u00edo M. Wiebe P. Peterson P. G\u00e9rard-Marchant K. Sheppard T. Reddy W. Weckesser H. Abbasi C. G. and T. E. Oliphant. 2020. Array programming with NumPy. Nature (2020).","DOI":"10.1038\/s41586-020-2649-2"},{"key":"e_1_3_2_2_15_1","volume-title":"KDD '14 AdKDD Workshop.","author":"He X.","unstructured":"X. He , O. Pan , J.and Jin, T . Xu, B. Liu, T. Xu, Y. Shi, A. Atallah, R. Herbrich, S. Bowers, and J. Q. Candela. 2014. Practical Lessons from Predicting Clicks on Ads at Facebook . In KDD '14 AdKDD Workshop. X. He, O. Pan, J.and Jin, T. Xu, B. Liu, T. Xu, Y. Shi, A. Atallah, R. Herbrich, S. Bowers, and J. Q. Candela. 2014. Practical Lessons from Predicting Clicks on Ads at Facebook. In KDD '14 AdKDD Workshop."},{"key":"e_1_3_2_2_16_1","unstructured":"E. Ie C. Hsu M. Mladenov V. Jain S. Narvekar J. Wang R. Wu and C. Boutilier. 2019. RecSim: A Configurable Simulation Platform for Recommender Systems. https:\/\/arxiv.org\/abs\/1909.04847  E. Ie C. Hsu M. Mladenov V. Jain S. Narvekar J. Wang R. Wu and C. Boutilier. 2019. RecSim: A Configurable Simulation Platform for Recommender Systems. https:\/\/arxiv.org\/abs\/1909.04847"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1198\/106186008X320456"},{"key":"e_1_3_2_2_18_1","volume-title":"An Empirical Evaluation of Doubly Robust Learning for Recommendation. In RecSys '20 REVEAL Workshop.","author":"Jeunen O.","unstructured":"O. Jeunen and B. Goethals . 2020 . An Empirical Evaluation of Doubly Robust Learning for Recommendation. In RecSys '20 REVEAL Workshop. O. Jeunen and B. Goethals. 2020. An Empirical Evaluation of Doubly Robust Learning for Recommendation. In RecSys '20 REVEAL Workshop."},{"key":"e_1_3_2_2_19_1","volume-title":"Pessimistic Reward Models for Off-Policy Learning in Recommendation. In RecSys '21","author":"Jeunen O.","unstructured":"O. Jeunen and B. Goethals . 2021 . Pessimistic Reward Models for Off-Policy Learning in Recommendation. In RecSys '21 . O. Jeunen and B. Goethals. 2021. Pessimistic Reward Models for Off-Policy Learning in Recommendation. In RecSys '21."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"crossref","unstructured":"O. Jeunen and B. Goethals. 2023. Pessimistic Decision-Making for Recommender Systems. ACM ToRS (2023).  O. Jeunen and B. Goethals. 2023. Pessimistic Decision-Making for Recommender Systems. ACM ToRS (2023).","DOI":"10.1145\/3568029"},{"key":"e_1_3_2_2_21_1","volume-title":"Joint Policy-Value Learning for Recommendation. In KDD '20","author":"Jeunen O.","unstructured":"O. Jeunen , D. Rohde , F. Vasile , and M. Bompaire . 2020 . Joint Policy-Value Learning for Recommendation. In KDD '20 . O. Jeunen, D. Rohde, F. Vasile, and M. Bompaire. 2020. Joint Policy-Value Learning for Recommendation. In KDD '20."},{"key":"e_1_3_2_2_22_1","volume-title":"AAAI '23 AI4WebAds Workshop.","author":"Jeunen O.","unstructured":"O. Jeunen , L. Stavrogiannis , A. Sayedi , and B. Allison . 2023. A Probabilistic Framework to Learn Auction Mechanisms via Gradient Descent . In AAAI '23 AI4WebAds Workshop. O. Jeunen, L. Stavrogiannis, A. Sayedi, and B. Allison. 2023. A Probabilistic Framework to Learn Auction Mechanisms via Gradient Descent. In AAAI '23 AI4WebAds Workshop."},{"key":"e_1_3_2_2_23_1","volume-title":"Adaptive Bid Shading Optimization of First-Price Ad Inventory. In ACC '21","author":"Karlsson N.","unstructured":"N. Karlsson and Q. Sang . 2021 . Adaptive Bid Shading Optimization of First-Price Ad Inventory. In ACC '21 . N. Karlsson and Q. Sang. 2021. Adaptive Bid Shading Optimization of First-Price Ad Inventory. In ACC '21."},{"key":"e_1_3_2_2_24_1","volume-title":"Adam: A Method for Stochastic Optimization. https:\/\/arxiv.org\/abs\/1412.6980","author":"Kingma D. P.","year":"2014","unstructured":"D. P. Kingma and J. Ba . 2014 . Adam: A Method for Stochastic Optimization. https:\/\/arxiv.org\/abs\/1412.6980 D. P. Kingma and J. Ba. 2014. Adam: A Method for Stochastic Optimization. https:\/\/arxiv.org\/abs\/1412.6980"},{"key":"e_1_3_2_2_25_1","volume-title":"Variational Dropout and the Local Reparameterization Trick. In NeurIPS '15","author":"Kingma D. P","unstructured":"D. P Kingma , T. Salimans , and M. Welling . 2015 . Variational Dropout and the Local Reparameterization Trick. In NeurIPS '15 . D. P Kingma, T. Salimans, and M. Welling. 2015. Variational Dropout and the Local Reparameterization Trick. In NeurIPS '15."},{"key":"e_1_3_2_2_26_1","unstructured":"D. P. Kingma and M. Welling. 2013. Auto-Encoding Variational Bayes. https:\/\/arxiv.org\/abs\/1312.6114  D. P. Kingma and M. Welling. 2013. Auto-Encoding Variational Bayes. https:\/\/arxiv.org\/abs\/1312.6114"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.263"},{"key":"e_1_3_2_2_28_1","volume-title":"Numba: A LLVM-Based Python JIT Compiler. In LLVM '15","author":"Lam S. K.","unstructured":"S. K. Lam , A. Pitrou , and S. Seibert . 2015 . Numba: A LLVM-Based Python JIT Compiler. In LLVM '15 . S. K. Lam, A. Pitrou, and S. Seibert. 2015. Numba: A LLVM-Based Python JIT Compiler. In LLVM '15."},{"key":"e_1_3_2_2_29_1","volume-title":"Certified Monotonic Neural Networks. In NeurIPS '20","author":"Liu X.","unstructured":"X. Liu , X. Han , N. Z. , and Q. Liu . 2020 . Certified Monotonic Neural Networks. In NeurIPS '20 . X. Liu, X. Han, N. Z., and Q. Liu. 2020. Certified Monotonic Neural Networks. In NeurIPS '20."},{"key":"e_1_3_2_2_30_1","volume-title":"Neural Auction: End-to-End Learning of Auction Mechanisms for E-Commerce Advertising. In KDD '21","author":"Liu X.","unstructured":"X. Liu , C. Yu , Z. Zhang , Z. Zheng , Y. Rong , H. Lv , D. Huo , Y. Wang , D. Chen , J. Xu , F. Wu , G. Chen , and X. Zhu . 2021 . Neural Auction: End-to-End Learning of Auction Mechanisms for E-Commerce Advertising. In KDD '21 . X. Liu, C. Yu, Z. Zhang, Z. Zheng, Y. Rong, H. Lv, D. Huo, Y. Wang, D. Chen, J. Xu, F. Wu, G. Chen, and X. Zhu. 2021. Neural Auction: End-to-End Learning of Auction Mechanisms for E-Commerce Advertising. In KDD '21."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"crossref","unstructured":"Y. A. Malkov and D. A. Yashunin. 2020. Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World Graphs. IEEE TPAMI (2020).  Y. A. Malkov and D. A. Yashunin. 2020. Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World Graphs. IEEE TPAMI (2020).","DOI":"10.1109\/TPAMI.2018.2889473"},{"key":"e_1_3_2_2_32_1","first-page":"178","article-title":"From the Help Desk","volume":"3","author":"McDowell A.","year":"2003","unstructured":"A. McDowell . 2003 . From the Help Desk : Hurdle Models. The Stata Journal , Vol. 3 , 2 (2003), 178 -- 184 . A. McDowell. 2003. From the Help Desk: Hurdle Models. The Stata Journal, Vol. 3, 2 (2003), 178--184.","journal-title":"Hurdle Models. The Stata Journal"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2488200"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1287\/moor.6.1.58"},{"key":"e_1_3_2_2_35_1","unstructured":"A. B. Owen. 2013. Monte Carlo theory methods and examples.  A. B. Owen. 2013. Monte Carlo theory methods and examples."},{"key":"e_1_3_2_2_36_1","volume-title":"KDD '20 AdKDD Workshop.","author":"Pan S.","unstructured":"S. Pan , B. Kitts , T. Zhou , H. He , B. Shetty , a. Flores, D. Gligorijevic , J. Pan , T. Mao , S. Gultekin , and J. Zhang . 2020. Bid Shading by Win-Rate Estimation and Surplus Maximization . In KDD '20 AdKDD Workshop. S. Pan, B. Kitts, T. Zhou, H. He, B. Shetty, a. Flores, D. Gligorijevic, J. Pan, T. Mao, S. Gultekin, and J. Zhang. 2020. Bid Shading by Win-Rate Estimation and Surplus Maximization. In KDD '20 AdKDD Workshop."},{"key":"e_1_3_2_2_37_1","volume-title":"High-Performance Deep Learning Library. In NeurIPS '19","author":"Paszke A.","unstructured":"A. Paszke , S. Gross , F. Massa , A. Lerer , J. Bradbury , G. Chanan , T. Killeen , Z. Lin , N. Gimelshein , L. Antiga , A. Desmaison , A. Kopf , E. Yang , Z. DeVito , M. Raison , A. Tejani , S. Chilamkurthy , B. Steiner , L. Fang , J. Bai , and S. Chintala . 2019. PyTorch: An Imperative Style , High-Performance Deep Learning Library. In NeurIPS '19 . A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, A. Desmaison, A. Kopf, E. Yang, Z. DeVito, M. Raison, A. Tejani, S. Chilamkurthy, B. Steiner, L. Fang, J. Bai, and S. Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In NeurIPS '19."},{"key":"e_1_3_2_2_38_1","volume-title":"RecSys '18 REVEAL Workshop.","author":"Rohde D.","unstructured":"D. Rohde , S. Bonner , T. Dunlop , F. Vasile , and A. Karatzoglou . 2018. RecoGym: A Reinforcement Learning Environment for the problem of Product Recommendation in Online Advertising . In RecSys '18 REVEAL Workshop. D. Rohde, S. Bonner, T. Dunlop, F. Vasile, and A. Karatzoglou. 2018. RecoGym: A Reinforcement Learning Environment for the problem of Product Recommendation in Online Advertising. In RecSys '18 REVEAL Workshop."},{"key":"e_1_3_2_2_39_1","volume-title":"Trust Region Policy Optimization. In ICML '15","author":"Schulman J.","unstructured":"J. Schulman , S. Levine , P. Abbeel , M. Jordan , and P. Moritz . 2015 . Trust Region Policy Optimization. In ICML '15 . J. Schulman, S. Levine, P. Abbeel, M. Jordan, and P. Moritz. 2015. Trust Region Policy Optimization. In ICML '15."},{"key":"e_1_3_2_2_40_1","unstructured":"J. Schulman F. Wolski P. Dhariwal A. Radford and O. Klimov. 2017. Proximal Policy Optimization Algorithms. https:\/\/arxiv.org\/abs\/1707.06347  J. Schulman F. Wolski P. Dhariwal A. Radford and O. Klimov. 2017. Proximal Policy Optimization Algorithms. https:\/\/arxiv.org\/abs\/1707.06347"},{"key":"e_1_3_2_2_41_1","volume-title":"Distributionally Robust Policy Evaluation and Learning in Offline Contextual Bandits. In ICML '20","author":"Si N.","unstructured":"N. Si , F. Zhang , Z. Zhou , and J. Blanchet . 2020 . Distributionally Robust Policy Evaluation and Learning in Offline Contextual Bandits. In ICML '20 . N. Si, F. Zhang, Z. Zhou, and J. Blanchet. 2020. Distributionally Robust Policy Evaluation and Learning in Offline Contextual Bandits. In ICML '20."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1017\/S1062798700002660"},{"key":"e_1_3_2_2_43_1","volume-title":"ICML '20","author":"Su Y.","unstructured":"Y. Su , M. Dimakopoulou , A. Krishnamurthy , and M. Dudik . 2020. Doubly robust off-policy evaluation with shrinkage . In ICML '20 . Y. Su, M. Dimakopoulou, A. Krishnamurthy, and M. Dudik. 2020. Doubly robust off-policy evaluation with shrinkage. In ICML '20."},{"key":"e_1_3_2_2_44_1","volume-title":"CAB: Continuous Adaptive Blending for Policy Evaluation and Learning. In ICML '19","author":"Su Y.","unstructured":"Y. Su , L. Wang , M. Santacatterina , and T. Joachims . 2019 . CAB: Continuous Adaptive Blending for Policy Evaluation and Learning. In ICML '19 . Y. Su, L. Wang, M. Santacatterina, and T. Joachims. 2019. CAB: Continuous Adaptive Blending for Policy Evaluation and Learning. In ICML '19."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"crossref","unstructured":"A. Swaminathan and T. Joachims. 2015. Batch learning from logged bandit feedback through counterfactual risk minimization. JMLR (2015).  A. Swaminathan and T. Joachims. 2015. Batch learning from logged bandit feedback through counterfactual risk minimization. JMLR (2015).","DOI":"10.1145\/2740908.2742564"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1540-6261.1961.tb02789.x"},{"key":"e_1_3_2_2_47_1","volume-title":"Deep & Cross Network for Ad Click Predictions. In KDD '17 AdKDD Workshop.","author":"Wang R.","unstructured":"R. Wang , B. Fu , G. Fu , and M. Wang . 2017 . Deep & Cross Network for Ad Click Predictions. In KDD '17 AdKDD Workshop. R. Wang, B. Fu, G. Fu, and M. Wang. 2017. Deep & Cross Network for Ad Click Predictions. In KDD '17 AdKDD Workshop."},{"key":"e_1_3_2_2_48_1","volume-title":"CIKM '19","author":"Wu D.","unstructured":"D. Wu , X. Chen , X. Yang , H. Wang , Q. Tan , X. Zhang , J. Xu , and K. Gai . 2018. Budget Constrained Bidding by Model-Free Reinforcement Learning in Display Advertising . In CIKM '19 . D. Wu, X. Chen, X. Yang, H. Wang, Q. Tan, X. Zhang, J. Xu, and K. Gai. 2018. Budget Constrained Bidding by Model-Free Reinforcement Learning in Display Advertising. In CIKM '19."},{"key":"e_1_3_2_2_49_1","volume-title":"AISTATS '19","author":"Xu M.","unstructured":"M. Xu , M. Quiroz , R. Kohn , and S. A. Sisson . 2019. Variance reduction properties of the reparameterization trick . In AISTATS '19 . M. Xu, M. Quiroz, R. Kohn, and S. A. Sisson. 2019. Variance reduction properties of the reparameterization trick. In AISTATS '19."},{"key":"e_1_3_2_2_50_1","volume-title":"Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality. In ICML '21","author":"Xu T.","unstructured":"T. Xu , Z. Yang , Z. Wang , and Y. Liang . 2021 . Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality. In ICML '21 . T. Xu, Z. Yang, Z. Wang, and Y. Liang. 2021. Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality. In ICML '21."},{"key":"e_1_3_2_2_51_1","volume-title":"KDD '19","author":"Yang X.","unstructured":"X. Yang , Y. Li , H. Wang , D. Wu , Q. Tan , J. Xu , and K. Gai . 2019. Bid Optimization by Multivariable Control in Display Advertising . In KDD '19 . X. Yang, Y. Li, H. Wang, D. Wu, Q. Tan, J. Xu, and K. Gai. 2019. Bid Optimization by Multivariable Control in Display Advertising. In KDD '19."},{"key":"e_1_3_2_2_52_1","volume-title":"MEOW: A Space-Efficient Nonparametric Bid Shading Algorithm. In KDD '21","author":"Zhang W.","unstructured":"W. Zhang , B. Kitts , Y. Han , Z. Zhou , T. Mao , H. He , S. Pan , A. Flores , S. Gultekin , and T. Weissman . 2021a . MEOW: A Space-Efficient Nonparametric Bid Shading Algorithm. In KDD '21 . W. Zhang, B. Kitts, Y. Han, Z. Zhou, T. Mao, H. He, S. Pan, A. Flores, S. Gultekin, and T. Weissman. 2021a. MEOW: A Space-Efficient Nonparametric Bid Shading Algorithm. In KDD '21."},{"key":"e_1_3_2_2_53_1","volume-title":"Optimizing Multiple Performance Metrics with Deep GSP Auctions for E-Commerce Advertising. In WSDM '21","author":"Zhang Z.","unstructured":"Z. Zhang , X. Liu , Z. Zheng , C. Zhang , M. Xu , J. Pan , C. Yu , F. Wu , J. Xu , and K. Gai . 2021b . Optimizing Multiple Performance Metrics with Deep GSP Auctions for E-Commerce Advertising. In WSDM '21 . Z. Zhang, X. Liu, Z. Zheng, C. Zhang, M. Xu, J. Pan, C. Yu, F. Wu, J. Xu, and K. Gai. 2021b. Optimizing Multiple Performance Metrics with Deep GSP Auctions for E-Commerce Advertising. In WSDM '21."},{"key":"e_1_3_2_2_54_1","volume-title":"An Efficient Deep Distribution Network for Bid Shading in First-Price Auctions. In KDD '21","author":"Zhou T.","unstructured":"T. Zhou , H. He , S. Pan , N. Karlsson , B. Shetty , B. Kitts , D. Gligorijevic , S. Gultekin , T. Mao , J. Pan , J. Zhang , and A. Flores . 2021 . An Efficient Deep Distribution Network for Bid Shading in First-Price Auctions. In KDD '21 . T. Zhou, H. He, S. Pan, N. Karlsson, B. Shetty, B. Kitts, D. Gligorijevic, S. Gultekin, T. Mao, J. Pan, J. Zhang, and A. Flores. 2021. An Efficient Deep Distribution Network for Bid Shading in First-Price Auctions. In KDD '21."}],"event":{"name":"KDD '23: The 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Long Beach CA USA","acronym":"KDD '23","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3580305.3599877","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3580305.3599877","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:24Z","timestamp":1750182564000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3580305.3599877"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,4]]},"references-count":54,"alternative-id":["10.1145\/3580305.3599877","10.1145\/3580305"],"URL":"https:\/\/doi.org\/10.1145\/3580305.3599877","relation":{},"subject":[],"published":{"date-parts":[[2023,8,4]]},"assertion":[{"value":"2023-08-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}