Picture for Yuhua Zhu

Yuhua Zhu

On Bellman equations for continuous-time policy evaluation I: discretization and approximation

Add code
Jul 08, 2024
Viaarxiv icon

FedCBO: Reaching Group Consensus in Clustered Federated Learning through Consensus-based Optimization

Add code
May 04, 2023
Figure 1 for FedCBO: Reaching Group Consensus in Clustered Federated Learning through Consensus-based Optimization
Figure 2 for FedCBO: Reaching Group Consensus in Clustered Federated Learning through Consensus-based Optimization
Figure 3 for FedCBO: Reaching Group Consensus in Clustered Federated Learning through Consensus-based Optimization
Figure 4 for FedCBO: Reaching Group Consensus in Clustered Federated Learning through Consensus-based Optimization
Viaarxiv icon

Continuous-in-time Limit for Bayesian Bandits

Add code
Oct 14, 2022
Figure 1 for Continuous-in-time Limit for Bayesian Bandits
Figure 2 for Continuous-in-time Limit for Bayesian Bandits
Figure 3 for Continuous-in-time Limit for Bayesian Bandits
Figure 4 for Continuous-in-time Limit for Bayesian Bandits
Viaarxiv icon

On Large Batch Training and Sharp Minima: A Fokker-Planck Perspective

Add code
Dec 02, 2021
Figure 1 for On Large Batch Training and Sharp Minima: A Fokker-Planck Perspective
Figure 2 for On Large Batch Training and Sharp Minima: A Fokker-Planck Perspective
Figure 3 for On Large Batch Training and Sharp Minima: A Fokker-Planck Perspective
Figure 4 for On Large Batch Training and Sharp Minima: A Fokker-Planck Perspective
Viaarxiv icon

Operator Augmentation for Model-based Policy Evaluation

Add code
Oct 25, 2021
Figure 1 for Operator Augmentation for Model-based Policy Evaluation
Figure 2 for Operator Augmentation for Model-based Policy Evaluation
Figure 3 for Operator Augmentation for Model-based Policy Evaluation
Figure 4 for Operator Augmentation for Model-based Policy Evaluation
Viaarxiv icon

Variational Actor-Critic Algorithms

Add code
Aug 15, 2021
Figure 1 for Variational Actor-Critic Algorithms
Figure 2 for Variational Actor-Critic Algorithms
Figure 3 for Variational Actor-Critic Algorithms
Figure 4 for Variational Actor-Critic Algorithms
Viaarxiv icon

Why resampling outperforms reweighting for correcting sampling bias

Add code
Sep 28, 2020
Figure 1 for Why resampling outperforms reweighting for correcting sampling bias
Figure 2 for Why resampling outperforms reweighting for correcting sampling bias
Figure 3 for Why resampling outperforms reweighting for correcting sampling bias
Figure 4 for Why resampling outperforms reweighting for correcting sampling bias
Viaarxiv icon

Borrowing From the Future: Addressing Double Sampling in Model-free Control

Add code
Jun 11, 2020
Figure 1 for Borrowing From the Future: Addressing Double Sampling in Model-free Control
Figure 2 for Borrowing From the Future: Addressing Double Sampling in Model-free Control
Figure 3 for Borrowing From the Future: Addressing Double Sampling in Model-free Control
Figure 4 for Borrowing From the Future: Addressing Double Sampling in Model-free Control
Viaarxiv icon

Towards Theoretical Understanding of Large Batch Training in Stochastic Gradient Descent

Add code
Dec 03, 2018
Figure 1 for Towards Theoretical Understanding of Large Batch Training in Stochastic Gradient Descent
Figure 2 for Towards Theoretical Understanding of Large Batch Training in Stochastic Gradient Descent
Figure 3 for Towards Theoretical Understanding of Large Batch Training in Stochastic Gradient Descent
Figure 4 for Towards Theoretical Understanding of Large Batch Training in Stochastic Gradient Descent
Viaarxiv icon