1 code implementation • 18 Nov 2020 • Rong Zhu, Ziniu Wu, Yuxing Han, Kai Zeng, Andreas Pfadler, Zhengping Qian, Jingren Zhou, Bin Cui
Despite decades of research, existing methods either over simplify the models only using independent factorization which leads to inaccurate estimates, or over complicate them by lossless conditional factorization without any independent assumption which results in slow probability computation.
1 code implementation • 29 Dec 2020 • Ziniu Wu, Amir Shaikhha, Rong Zhu, Kai Zeng, Yuxing Han, Jingren Zhou
Recently proposed deep learning based methods largely improve the estimation accuracy but their performance can be greatly affected by data and often difficult for system deployment.
1 code implementation • 13 Sep 2021 • Yuxing Han, Ziniu Wu, Peizhi Wu, Rong Zhu, Jingyi Yang, Liang Wei Tan, Kai Zeng, Gao Cong, Yanzhao Qin, Andreas Pfadler, Zhengping Qian, Jingren Zhou, Jiangneng Li, Bin Cui
Therefore, we propose a new metric P-Error to evaluate the performance of CardEst methods, which overcomes the limitation of Q-Error and is able to reflect the overall end-to-end performance of CardEst methods.
1 code implementation • 17 Jul 2018 • E. Kelly Buchanan, Ian Kinsella, Ding Zhou, Rong Zhu, Pengcheng Zhou, Felipe Gerhard, John Ferrante, Ying Ma, Sharon Kim, Mohammed Shaik, Yajie Liang, Rongwen Lu, Jacob Reimer, Paul Fahey, Taliah Muhammad, Graham Dempsey, Elizabeth Hillman, Na Ji, Andreas Tolias, Liam Paninski
Calcium imaging has revolutionized systems neuroscience, providing the ability to image large neural populations with single-cell resolution.
1 code implementation • 14 Feb 2023 • Rong Zhu, Wei Chen, Bolin Ding, Xingguang Chen, Andreas Pfadler, Ziniu Wu, Jingren Zhou
In this paper, we introduce a learning-to-rank query optimizer, called Lero, which builds on top of a native query optimizer and continuously learns to improve the optimization performance.
1 code implementation • 6 May 2021 • Ziniu Wu, Pei Yu, Peilun Yang, Rong Zhu, Yuxing Han, Yaliang Li, Defu Lian, Kai Zeng, Jingren Zhou
We propose to explore the transferabilities of the ML methods both across tasks and across DBs to tackle these fundamental drawbacks.
1 code implementation • NeurIPS 2021 • Rong Zhu, Mattia Rigotti
Bayesian exploration strategies like Thompson Sampling resolve this trade-off in a principled way by modeling and updating the distribution of the parameters of the action-value function, the outcome model of the environment.
no code implementations • 10 Apr 2018 • Rong Zhu, Jiming Jiang
For optimization on large-scale data, exactly calculating its solution may be computationally difficulty because of the large size of the data.
no code implementations • 3 Feb 2017 • HaiYing Wang, Rong Zhu, Ping Ma
In this paper, we propose fast subsampling algorithms to efficiently approximate the maximum likelihood estimate in logistic regression.
no code implementations • NeurIPS 2016 • Rong Zhu
In modern data analysis, random sampling is an efficient and widely-used strategy to overcome the computational difficulties brought by large sample size.
no code implementations • 7 Sep 2015 • Rong Zhu
Subsampling is one of efficient strategies to handle this problem.
no code implementations • 17 Sep 2015 • Rong Zhu, Ping Ma, Michael W. Mahoney, Bin Yu
For unweighted estimation algorithm, we show that its resulting subsample estimator is not consistent to the full sample OLS estimator.
no code implementations • 23 Feb 2019 • Rong Zhu, Kun Zhao, Hongxia Yang, Wei. Lin, Chang Zhou, Baole Ai, Yong Li, Jingren Zhou
An increasing number of machine learning tasks require dealing with large graph datasets, which capture rich and complex relationship among potentially billions of elements.
Distributed, Parallel, and Cluster Computing
no code implementations • ICLR 2020 • Rong Zhu, Sheng Yang, Andreas Pfadler, Zhengping Qian, Jingren Zhou
We apply a reinforcement learning (RL) based approach to learning optimal synchronization policies used for Parameter Server-based distributed training of machine learning models with Stochastic Gradient Descent (SGD).
no code implementations • 1 Jan 2021 • Rong Zhu, James Murray
Off-policy learning algorithms, in which an agent updates the value function of the optimal policy while selecting actions using an independent exploration policy, provide an effective solution to the explore-exploit tradeoff and have proven to be of great practical value in reinforcement learning.
no code implementations • 18 Nov 2020 • Ziniu Wu, Rong Zhu, Andreas Pfadler, Yuxing Han, Jiangneng Li, Zhengping Qian, Kai Zeng, Jingren Zhou
We introduce factorize sum split product networks (FSPNs), a new class of probabilistic graphical models (PGMs).
no code implementations • 2 Dec 2020 • Rong Zhu, Mattia Rigotti
The Q-learning algorithm is known to be affected by the maximization bias, i. e. the systematic overestimation of action values, an important issue that has recently received renewed attention.
no code implementations • 7 Dec 2020 • Rong Zhu, Andreas Pfadler, Ziniu Wu, Yuxing Han, Xiaoke Yang, Feng Ye, Zhenping Qian, Jingren Zhou, Bin Cui
To resolve this, we propose a new structure learning algorithm LEAST, which comprehensively fulfills our business requirements as it attains high accuracy, efficiency and scalability at the same time.
no code implementations • 21 May 2021 • Yingxia Jiao, Xiao Wang, Yu-Cheng Chou, Shouyuan Yang, Ge-Peng Ji, Rong Zhu, Ge Gao
Owing to the difficulties of mining spatial-temporal cues, the existing approaches for video salient object detection (VSOD) are limited in understanding complex and noisy scenarios, and often fail in inferring prominent objects.
no code implementations • 23 Jun 2021 • Rong Zhu, Branislav Kveton
It is well known that side information, such as the prior distribution of arm means in Thompson sampling, can improve the statistical efficiency of the bandit algorithm.
no code implementations • 29 Sep 2021 • Rong Zhu, Mattia Rigotti
Effectively tackling the \emph{exploration-exploitation dilemma} is still a major challenge in reinforcement learning.
no code implementations • 7 Dec 2021 • Rong Zhu, Tianjing Zeng, Andreas Pfadler, Wei Chen, Bolin Ding, Jingren Zhou
Cardinality estimation (CardEst), a central component of the query optimizer, plays a significant role in generating high-quality query plans in DBMS.
no code implementations • 29 Dec 2021 • Andreas Pfadler, Rong Zhu, Wei Chen, Botong Huang, Tianjing Zeng, Bolin Ding, Jingren Zhou
Based on the high level architecture, we then describe a concrete implementation of Baihe for PostgreSQL and present example use cases for learned query optimizers.
no code implementations • 26 Oct 2022 • Rong Zhu, Branislav Kveton
Our experiments show that RoLinTS is comparably statistically efficient to the classic methods when the misspecification is low, more robust when the misspecification is high, and significantly more computationally efficient than its naive implementation.