Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Zhou, Norm"'
Autor:
Garrard, Mia, Wang, Hanson, Letham, Ben, Singh, Shaun, Kazerouni, Abbas, Tan, Sarah, Wang, Zehui, Huang, Yin, Hu, Yichun, Zhou, Chad, Zhou, Norm, Bakshy, Eytan
Many organizations measure treatment effects via an experimentation platform to evaluate the casual effect of product variations prior to full-scale deployment. However, standard experimentation platforms do not perform optimally for end user populat
Externí odkaz:
http://arxiv.org/abs/2303.17648
Autor:
Markov, Igor L., Apostolopoulos, Pavlos A., Garrard, Mia R., Qie, Tanya, Huang, Yin, Gupta, Tanvi, Li, Anika, Cardoso, Cesar, Han, George, Maghsoudian, Ryan, Zhou, Norm
ML platforms help enable intelligent data-driven applications and maintain them with limited engineering effort. Upon sufficiently broad adoption, such platforms reach economies of scale that bring greater component reuse while improving efficiency o
Externí odkaz:
http://arxiv.org/abs/2302.14139
Autor:
Markov, Igor L., Wang, Hanson, Kasturi, Nitya, Singh, Shaun, Yuen, Sze Wai, Garrard, Mia, Tran, Sarah, Huang, Yin, Wang, Zehui, Glotov, Igor, Gupta, Tanvi, Huang, Boshuang, Chen, Peng, Xie, Xiaowen, Belkin, Michael, Uryasev, Sal, Howie, Sam, Bakshy, Eytan, Zhou, Norm
Modern software systems and products increasingly rely on machine learning models to make data-driven decisions based on interactions with users, infrastructure and other systems. For broader adoption, this practice must (i) accommodate product engin
Externí odkaz:
http://arxiv.org/abs/2110.07554
Autor:
Apostolopoulos, Pavlos Athanasios, Wang, Zehui, Wang, Hanson, Zhou, Chad, Virochsiri, Kittipat, Zhou, Norm, Markov, Igor L.
Publikováno v:
2nd Offline Reinforcement Learning Workshop at NeurIPS 2021
Large-scale Web-based services present opportunities for improving UI policies based on observed user interactions. We address challenges of learning such policies through model-free offline Reinforcement Learning (RL) with off-policy training. Deplo
Externí odkaz:
http://arxiv.org/abs/2102.05612
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Markov, Igor L., Wang, Hanson, Kasturi, Nitya, Singh, Shaun, Yuen, Sze Wai, Garrard, Mia, Tran, Sarah, Huang, Yin, Wang, Zehui, Glotov, Igor, Gupta, Tanvi, Huang, Boshuang, Chen, Peng, Xie, Xiaowen, Belkin, Michael, Uryasev, Sal, Howie, Sam, Bakshy, Eytan, Zhou, Norm
Publikováno v:
Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.
Modern software systems and products increasingly rely on machine learning models to make data-driven decisions based on interactions with users, infrastructure and other systems. For broader adoption, this practice must (i) accommodate product engin