Search Results for author: Dengyong Zhou

Found 22 papers, 4 papers with code

Post-training Quantization with Multiple Points: Mixed Precision without Mixed Precision

no code implementations20 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.

object-detection Object Detection +1

Neural Phrase-to-Phrase Machine Translation

no code implementations6 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).

Decoder Machine Translation +1

Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation

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.

On the Discrimination-Generalization Tradeoff in GANs

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.

Generalization Bounds

Action-depedent Control Variates for Policy Optimization via Stein's Identity

2 code implementations30 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.

Policy Gradient Methods reinforcement-learning +1

Provably Optimal Algorithms for Generalized Linear Contextual Bandits

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.

Multi-Armed Bandits News Recommendation

Stochastic Variance Reduction Methods for Policy Evaluation

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.

Reinforcement Learning (RL)

Sequence Modeling via Segmentations

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.

Segmentation speech-recognition +3

Neuro-Symbolic Program Synthesis

no code implementations6 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).

Program induction Program Synthesis

Exact Exponent in Optimal Rates for Crowdsourcing

no code implementations25 May 2016 Chao Gao, Yu Lu, Dengyong Zhou

In many machine learning applications, crowdsourcing has become the primary means for label collection.

Approval Voting and Incentives in Crowdsourcing

no code implementations19 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.

On the Impossibility of Convex Inference in Human Computation

no code implementations21 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.

Double or Nothing: Multiplicative Incentive Mechanisms for Crowdsourcing

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.

Statistical Decision Making for Optimal Budget Allocation in Crowd Labeling

no code implementations12 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.

Decision Making

Minimax Optimal Convergence Rates for Estimating Ground Truth from Crowdsourced Labels

no code implementations22 Oct 2013 Chao Gao, Dengyong Zhou

Crowdsourcing has become a primary means for label collection in many real-world machine learning applications.

Error Rate Bounds in Crowdsourcing Models

no code implementations10 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.

Cannot find the paper you are looking for? You can Submit a new open access paper.