Picture for Dengyong Zhou

Dengyong Zhou

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

Add code
Feb 24, 2020
Figure 1 for Post-training Quantization with Multiple Points: Mixed Precision without Mixed Precision
Figure 2 for Post-training Quantization with Multiple Points: Mixed Precision without Mixed Precision
Figure 3 for Post-training Quantization with Multiple Points: Mixed Precision without Mixed Precision
Figure 4 for Post-training Quantization with Multiple Points: Mixed Precision without Mixed Precision
Viaarxiv icon

Doubly Robust Bias Reduction in Infinite Horizon Off-Policy Estimation

Add code
Oct 16, 2019
Figure 1 for Doubly Robust Bias Reduction in Infinite Horizon Off-Policy Estimation
Figure 2 for Doubly Robust Bias Reduction in Infinite Horizon Off-Policy Estimation
Figure 3 for Doubly Robust Bias Reduction in Infinite Horizon Off-Policy Estimation
Viaarxiv icon

Neural Phrase-to-Phrase Machine Translation

Add code
Nov 06, 2018
Figure 1 for Neural Phrase-to-Phrase Machine Translation
Figure 2 for Neural Phrase-to-Phrase Machine Translation
Figure 3 for Neural Phrase-to-Phrase Machine Translation
Figure 4 for Neural Phrase-to-Phrase Machine Translation
Viaarxiv icon

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

Add code
Oct 29, 2018
Figure 1 for Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation
Figure 2 for Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation
Figure 3 for Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation
Figure 4 for Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation
Viaarxiv icon

Towards Neural Phrase-based Machine Translation

Add code
Sep 24, 2018
Figure 1 for Towards Neural Phrase-based Machine Translation
Figure 2 for Towards Neural Phrase-based Machine Translation
Figure 3 for Towards Neural Phrase-based Machine Translation
Figure 4 for Towards Neural Phrase-based Machine Translation
Viaarxiv icon

Sequence Modeling via Segmentations

Add code
Jul 18, 2018
Figure 1 for Sequence Modeling via Segmentations
Figure 2 for Sequence Modeling via Segmentations
Figure 3 for Sequence Modeling via Segmentations
Figure 4 for Sequence Modeling via Segmentations
Viaarxiv icon

On the Discrimination-Generalization Tradeoff in GANs

Add code
Feb 23, 2018
Figure 1 for On the Discrimination-Generalization Tradeoff in GANs
Figure 2 for On the Discrimination-Generalization Tradeoff in GANs
Figure 3 for On the Discrimination-Generalization Tradeoff in GANs
Figure 4 for On the Discrimination-Generalization Tradeoff in GANs
Viaarxiv icon

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

Add code
Feb 23, 2018
Figure 1 for Action-depedent Control Variates for Policy Optimization via Stein's Identity
Figure 2 for Action-depedent Control Variates for Policy Optimization via Stein's Identity
Figure 3 for Action-depedent Control Variates for Policy Optimization via Stein's Identity
Figure 4 for Action-depedent Control Variates for Policy Optimization via Stein's Identity
Viaarxiv icon

Provably Optimal Algorithms for Generalized Linear Contextual Bandits

Add code
Jun 18, 2017
Viaarxiv icon

Stochastic Variance Reduction Methods for Policy Evaluation

Add code
Jun 09, 2017
Figure 1 for Stochastic Variance Reduction Methods for Policy Evaluation
Figure 2 for Stochastic Variance Reduction Methods for Policy Evaluation
Figure 3 for Stochastic Variance Reduction Methods for Policy Evaluation
Figure 4 for Stochastic Variance Reduction Methods for Policy Evaluation
Viaarxiv icon