no code implementations • 20 Feb 2020 • Xingchao Liu, Mao Ye, Dengyong Zhou, Qiang Liu
We propose multipoint quantization, a quantization method that approximates a full-precision weight vector using a linear combination of multiple vectors of low-bit numbers; this is in contrast to typical quantization methods that approximate each weight using a single low precision number.
no code implementations • ICLR 2020 • Ziyang Tang, Yihao Feng, Lihong Li, Dengyong Zhou, Qiang Liu
Our method is doubly robust in that the bias vanishes when either the density ratio or the value function estimation is perfect.
no code implementations • 6 Nov 2018 • Jiangtao Feng, Lingpeng Kong, Po-Sen Huang, Chong Wang, Da Huang, Jiayuan Mao, Kan Qiao, Dengyong Zhou
We also design an efficient dynamic programming algorithm to decode segments that allows the model to be trained faster than the existing neural phrase-based machine translation method by Huang et al. (2018).
2 code implementations • NeurIPS 2018 • Qiang Liu, Lihong Li, Ziyang Tang, Dengyong Zhou
We consider the off-policy estimation problem of estimating the expected reward of a target policy using samples collected by a different behavior policy.
no code implementations • ICLR 2018 • Hao Liu*, Yihao Feng*, Yi Mao, Dengyong Zhou, Jian Peng, Qiang Liu
Policy gradient methods have achieved remarkable successes in solving challenging reinforcement learning problems.
no code implementations • ICLR 2018 • Pengchuan Zhang, Qiang Liu, Dengyong Zhou, Tao Xu, Xiaodong He
When evaluated with neural distance, our bounds show that generalization is guaranteed as long as the discriminator set is small enough, regardless of the size of the generator or hypothesis set.
2 code implementations • 30 Oct 2017 • Hao Liu, Yihao Feng, Yi Mao, Dengyong Zhou, Jian Peng, Qiang Liu
Policy gradient methods have achieved remarkable successes in solving challenging reinforcement learning problems.
4 code implementations • ICLR 2018 • Po-Sen Huang, Chong Wang, Sitao Huang, Dengyong Zhou, Li Deng
In this paper, we present Neural Phrase-based Machine Translation (NPMT).
Ranked #7 on Machine Translation on IWSLT2015 English-German
no code implementations • ICML 2017 • Lihong Li, Yu Lu, Dengyong Zhou
Contextual bandits are widely used in Internet services from news recommendation to advertising, and to Web search.
no code implementations • ICML 2017 • Simon S. Du, Jianshu Chen, Lihong Li, Lin Xiao, Dengyong Zhou
Policy evaluation is a crucial step in many reinforcement-learning procedures, which estimates a value function that predicts states' long-term value under a given policy.
2 code implementations • ICML 2017 • Chong Wang, Yining Wang, Po-Sen Huang, Abdel-rahman Mohamed, Dengyong Zhou, Li Deng
The probability of a segmented sequence is calculated as the product of the probabilities of all its segments, where each segment is modeled using existing tools such as recurrent neural networks.
no code implementations • 6 Nov 2016 • Emilio Parisotto, Abdel-rahman Mohamed, Rishabh Singh, Lihong Li, Dengyong Zhou, Pushmeet Kohli
While achieving impressive results, these approaches have a number of important limitations: (a) they are computationally expensive and hard to train, (b) a model has to be trained for each task (program) separately, and (c) it is hard to interpret or verify the correctness of the learnt mapping (as it is defined by a neural network).
no code implementations • 25 May 2016 • Chao Gao, Yu Lu, Dengyong Zhou
In many machine learning applications, crowdsourcing has become the primary means for label collection.
no code implementations • 25 Mar 2015 • Dengyong Zhou, Qiang Liu, John C. Platt, Christopher Meek, Nihar B. Shah
There is a rapidly increasing interest in crowdsourcing for data labeling.
no code implementations • 19 Feb 2015 • Nihar B. Shah, Dengyong Zhou, Yuval Peres
The growing need for labeled training data has made crowdsourcing an important part of machine learning.
no code implementations • 21 Nov 2014 • Nihar B. Shah, Dengyong Zhou
Human computation or crowdsourcing involves joint inference of the ground-truth-answers and the worker-abilities by optimizing an objective function, for instance, by maximizing the data likelihood based on an assumed underlying model.
no code implementations • NeurIPS 2015 • Nihar B. Shah, Dengyong Zhou
To address this fundamental challenge in crowdsourcing, we propose a simple payment mechanism to incentivize workers to answer only the questions that they are sure of and skip the rest.
no code implementations • NeurIPS 2014 • Yuchen Zhang, Xi Chen, Dengyong Zhou, Michael. I. Jordan
Crowdsourcing is a popular paradigm for effectively collecting labels at low cost.
no code implementations • 12 Mar 2014 • Xi Chen, Qihang Lin, Dengyong Zhou
In crowd labeling, a large amount of unlabeled data instances are outsourced to a crowd of workers.
no code implementations • 22 Oct 2013 • Chao Gao, Dengyong Zhou
Crowdsourcing has become a primary means for label collection in many real-world machine learning applications.
no code implementations • 10 Jul 2013 • Hongwei Li, Bin Yu, Dengyong Zhou
We show that the oracle Maximum A Posterior (MAP) rule approximately optimizes our upper bound on the mean error rate for any hyperplane binary labeling rule, and propose a simple data-driven weighted majority voting (WMV) rule (called one-step WMV) that attempts to approximate the oracle MAP and has a provable theoretical guarantee on the error rate.
no code implementations • NeurIPS 2012 • Dengyong Zhou, Sumit Basu, Yi Mao, John C. Platt
We propose a minimax entropy principle to improve the quality of these labels.