Zobrazeno 1 - 10
of 42
pro vyhledávání: '"Pfadler, Andreas"'
Autor:
Zhu, Rong, Chen, Wei, Ding, Bolin, Chen, Xingguang, Pfadler, Andreas, Wu, Ziniu, Zhou, Jingren
A recent line of works apply machine learning techniques to assist or rebuild cost-based query optimizers in DBMS. While exhibiting superiority in some benchmarks, their deficiencies, e.g., unstable performance, high training cost, and slow model upd
Externí odkaz:
http://arxiv.org/abs/2302.06873
In this paper, we propose a novel channel estimation scheme for pulse-shaped multicarrier systems using smoothness regularization for ultra-reliable low-latency communication (URLLC). It can be applied to any multicarrier system with or without linea
Externí odkaz:
http://arxiv.org/abs/2210.05233
Autor:
Pfadler, Andreas, Zhu, Rong, Chen, Wei, Huang, Botong, Zeng, Tianjing, Ding, Bolin, Zhou, Jingren
We present Baihe, a SysML Framework for AI-driven Databases. Using Baihe, an existing relational database system may be retrofitted to use learned components for query optimization or other common tasks, such as e.g. learned structure for indexing. T
Externí odkaz:
http://arxiv.org/abs/2112.14460
Cardinality estimation (CardEst), a central component of the query optimizer, plays a significant role in generating high-quality query plans in DBMS. The CardEst problem has been extensively studied in the last several decades, using both traditiona
Externí odkaz:
http://arxiv.org/abs/2112.03458
Autor:
Han, Yuxing, Wu, Ziniu, Wu, Peizhi, Zhu, Rong, Yang, Jingyi, Tan, Liang Wei, Zeng, Kai, Cong, Gao, Qin, Yanzhao, Pfadler, Andreas, Qian, Zhengping, Zhou, Jingren, Li, Jiangneng, Cui, Bin
Cardinality estimation (CardEst) plays a significant role in generating high-quality query plans for a query optimizer in DBMS. In the last decade, an increasing number of advanced CardEst methods (especially ML-based) have been proposed with outstan
Externí odkaz:
http://arxiv.org/abs/2109.05877
Autor:
Kousaridas, Apostolos, Manjunath, Ramya Panthangi, Perdomo, Jose Mauricio, Zhou, Chan, Zielinski, Ernst, Schmitz, Steffen, Pfadler, Andreas
5G communication system can support the demanding quality-of-service (QoS) requirements of many advanced vehicle-to-everything (V2X) use cases. However, the safe and efficient driving, especially of automated vehicles, may be affected by sudden chang
Externí odkaz:
http://arxiv.org/abs/2107.05000
Autor:
Zhu, Rong, Pfadler, Andreas, Wu, Ziniu, Han, Yuxing, Yang, Xiaoke, Ye, Feng, Qian, Zhenping, Zhou, Jingren, Cui, Bin
Structure Learning for Bayesian network (BN) is an important problem with extensive research. It plays central roles in a wide variety of applications in Alibaba Group. However, existing structure learning algorithms suffer from considerable limitati
Externí odkaz:
http://arxiv.org/abs/2012.03540
Autor:
Zhu, Rong, Wu, Ziniu, Han, Yuxing, Zeng, Kai, Pfadler, Andreas, Qian, Zhengping, Zhou, Jingren, Cui, Bin
Query optimizers rely on accurate cardinality estimation (CardEst) to produce good execution plans. The core problem of CardEst is how to model the rich joint distribution of attributes in an accurate and compact manner. Despite decades of research,
Externí odkaz:
http://arxiv.org/abs/2011.09022
Autor:
Wu, Ziniu, Zhu, Rong, Pfadler, Andreas, Han, Yuxing, Li, Jiangneng, Qian, Zhengping, Zeng, Kai, Zhou, Jingren
We introduce factorize sum split product networks (FSPNs), a new class of probabilistic graphical models (PGMs). FSPNs are designed to overcome the drawbacks of existing PGMs in terms of estimation accuracy and inference efficiency. Specifically, Bay
Externí odkaz:
http://arxiv.org/abs/2011.09020
Autor:
Chen, Wen, Huang, Pipei, Xu, Jiaming, Guo, Xin, Guo, Cheng, Sun, Fei, Li, Chao, Pfadler, Andreas, Zhao, Huan, Zhao, Binqiang
Increasing demand for fashion recommendation raises a lot of challenges for online shopping platforms and fashion communities. In particular, there exist two requirements for fashion outfit recommendation: the Compatibility of the generated fashion o
Externí odkaz:
http://arxiv.org/abs/1905.01866