144 citations · 966 across the 20 of their papers we have counts for
20 papers
Post-training Quantization with Multiple Points: Mixed Precision without Mixed Precision
Xingchao Liu, Mao Ye, Dengyong Zhou +1
We consider the post-training quantization problem, which discretizes the weights of pre-trained deep neural networks without re-training the model. We propose multipoint quantizat…
Doubly Robust Bias Reduction in Infinite Horizon Off-Policy Estimation
Ziyang Tang, Yihao Feng, Lihong Li +2
Infinite horizon off-policy policy evaluation is a highly challenging task due to the excessively large variance of typical importance sampling (IS) estimators. Recently, Liu et al…
Neural Phrase-to-Phrase Machine Translation
Jiangtao Feng, Lingpeng Kong, Po-Sen Huang +5
In this paper, we propose Neural Phrase-to-Phrase Machine Translation (NPMT). Our model uses a phrase attention mechanism to discover relevant input (source) segments that are…
Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation
Qiang Liu, Lihong Li, Ziyang Tang +1
We consider the off-policy estimation problem of estimating the expected reward of a target policy using samples collected by a different behavior policy. Importance sampling (IS)…
On the Discrimination-Generalization Tradeoff in GANs
Pengchuan Zhang, Qiang Liu, Dengyong Zhou +2
Generative adversarial training can be generally understood as minimizing certain moment matching loss defined by a set of discriminator functions, typically neural networks. The d…
Action-depedent Control Variates for Policy Optimization via Stein's Identity
Hao Liu, Yihao Feng, Yi Mao +3
Policy gradient methods have achieved remarkable successes in solving challenging reinforcement learning problems. However, it still often suffers from the large variance issue on…
Towards Neural Phrase-based Machine Translation
Po-Sen Huang, Chong Wang, Sitao Huang +2
In this paper, we present Neural Phrase-based Machine Translation (NPMT). Our method explicitly models the phrase structures in output sequences using Sleep-WAke Networks (SWAN), a…
Provably Optimal Algorithms for Generalized Linear Contextual Bandits
Lihong Li, Yu Lu, Dengyong Zhou
Contextual bandits are widely used in Internet services from news recommendation to advertising, and to Web search. Generalized linear models (logistical regression in particular)…
Stochastic Variance Reduction Methods for Policy Evaluation
Simon S. Du, Jianshu Chen, Lihong Li +2
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. In this…
Sequence Modeling via Segmentations
Chong Wang, Yining Wang, Po-Sen Huang +3
Segmental structure is a common pattern in many types of sequences such as phrases in human languages. In this paper, we present a probabilistic model for sequences via their segme…
Neuro-Symbolic Program Synthesis
Emilio Parisotto, Abdel-rahman Mohamed, Rishabh Singh +3
Recent years have seen the proposal of a number of neural architectures for the problem of Program Induction. Given a set of input-output examples, these architectures are able to…
Exact Exponent in Optimal Rates for Crowdsourcing
Chao Gao, Yu Lu, Dengyong Zhou
In many machine learning applications, crowdsourcing has become the primary means for label collection. In this paper, we study the optimal error rate for aggregating labels provid…
Regularized Minimax Conditional Entropy for Crowdsourcing
Dengyong Zhou, Qiang Liu, John C. Platt +2
There is a rapidly increasing interest in crowdsourcing for data labeling. By crowdsourcing, a large number of labels can be often quickly gathered at low cost. However, the labels…
Approval Voting and Incentives in Crowdsourcing
Nihar B. Shah, Dengyong Zhou, Yuval Peres
The growing need for labeled training data has made crowdsourcing an important part of machine learning. The quality of crowdsourced labels is, however, adversely affected by three…
On the Impossibility of Convex Inference in Human Computation
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 th…
Double or Nothing: Multiplicative Incentive Mechanisms for Crowdsourcing
Nihar B. Shah, Dengyong Zhou
Crowdsourcing has gained immense popularity in machine learning applications for obtaining large amounts of labeled data. Crowdsourcing is cheap and fast, but suffers from the prob…
Spectral Methods meet EM: A Provably Optimal Algorithm for Crowdsourcing
Yuchen Zhang, Xi Chen, Dengyong Zhou +1
Crowdsourcing is a popular paradigm for effectively collecting labels at low cost. The Dawid-Skene estimator has been widely used for inferring the true labels from the noisy label…
Statistical Decision Making for Optimal Budget Allocation in Crowd Labeling
Xi Chen, Qihang Lin, Dengyong Zhou
In crowd labeling, a large amount of unlabeled data instances are outsourced to a crowd of workers. Workers will be paid for each label they provide, but the labeling requester usu…
Minimax Optimal Convergence Rates for Estimating Ground Truth from Crowdsourced Labels
Chao Gao, Dengyong Zhou
Crowdsourcing has become a primary means for label collection in many real-world machine learning applications. A classical method for inferring the true labels from the noisy labe…
Error Rate Bounds in Crowdsourcing Models
Hongwei Li, Bin Yu, Dengyong Zhou
Crowdsourcing is an effective tool for human-powered computation on many tasks challenging for computers. In this paper, we provide finite-sample exponential bounds on the error ra…