Junyu Zhang

Orcid: 0000-0003-2194-9664

Affiliations:
  • National University of Singapore, Industrial Systems Engineering and Management, Singapore
  • Princeton University, Electrical and Computer Engineering, NJ, USA (2020-2021)
  • University of Minnesota, Department of Industrial and System Engineering, Twin Cities, Minneapolis, MN, USA (PhD 2020)


According to our database1, Junyu Zhang authored at least 38 papers between 2017 and 2026.

Collaborative distances:

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
Automated Reformulation of Robust Optimization via Memory-Augmented Large Language Models.
CoRR, May, 2026

Shuffling the Stochastic Mirror Descent via Dual Lipschitz Continuity and Kernel Conditioning.
CoRR, March, 2026

A New Kernel Regularity Condition for Distributed Mirror Descent: Broader Coverage and Simpler Analysis.
CoRR, March, 2026

2025
Non-Asymptotic Global Convergence of PPO-Clip.
CoRR, December, 2025

2024
General Procedure to Provide High-Probability Guarantees for Stochastic Saddle Point Problems.
J. Sci. Comput., July, 2024

Teamwork Reinforcement Learning With Concave Utilities.
IEEE Trans. Mob. Comput., May, 2024

Efficient First Order Method for Saddle Point Problems with Higher Order Smoothness.
SIAM J. Optim., 2024

On the Sample Complexity and Metastability of Heavy-tailed Policy Search in Continuous Control.
J. Mach. Learn. Res., 2024

First-Order Algorithms Without Lipschitz Gradient: A Sequential Local Optimization Approach.
INFORMS J. Optim., 2024

An Improved Finite-time Analysis of Temporal Difference Learning with Deep Neural Networks.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023
A Unified Primal-Dual Algorithm Framework for Inequality Constrained Problems.
J. Sci. Comput., November, 2023

Primal-Dual First-Order Methods for Affinely Constrained Multi-block Saddle Point Problems.
SIAM J. Optim., June, 2023

Provably Efficient Gauss-Newton Temporal Difference Learning Method with Function Approximation.
CoRR, 2023

2022
On the Divergence of Decentralized Nonconvex Optimization.
SIAM J. Optim., December, 2022

Adaptive Stochastic Variance Reduction for Subsampled Newton Method with Cubic Regularization.
INFORMS J. Optim., January, 2022

Stochastic variance-reduced prox-linear algorithms for nonconvex composite optimization.
Math. Program., 2022

On lower iteration complexity bounds for the convex concave saddle point problems.
Math. Program., 2022

Cubic Regularized Newton Method for the Saddle Point Models: A Global and Local Convergence Analysis.
J. Sci. Comput., 2022

A Near-Optimal Primal-Dual Method for Off-Policy Learning in CMDP.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Multi-Agent Reinforcement Learning with General Utilities via Decentralized Shadow Reward Actor-Critic.
Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

2021
MultiLevel Composite Stochastic Optimization via Nested Variance Reduction.
SIAM J. Optim., 2021

Cautious Reinforcement Learning via Distributional Risk in the Dual Domain.
IEEE J. Sel. Areas Inf. Theory, 2021

From Low Probability to High Confidence in Stochastic Convex Optimization.
J. Mach. Learn. Res., 2021

MARL with General Utilities via Decentralized Shadow Reward Actor-Critic.
CoRR, 2021

On the Convergence and Sample Efficiency of Variance-Reduced Policy Gradient Method.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Intermittent Communications in Decentralized Shadow Reward Actor-Critic.
Proceedings of the 2021 60th IEEE Conference on Decision and Control (CDC), 2021

Beyond Cumulative Returns via Reinforcement Learning over State-Action Occupancy Measures.
Proceedings of the 2021 American Control Conference, 2021

Generalization Bounds for Stochastic Saddle Point Problems.
Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020
Primal-dual optimization algorithms over Riemannian manifolds: an iteration complexity analysis.
Math. Program., 2020

On the Divergence of Decentralized Non-Convex Optimization.
CoRR, 2020

Variational Policy Gradient Method for Reinforcement Learning with General Utilities.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

FFT-based Gradient Sparsification for the Distributed Training of Deep Neural Networks.
Proceedings of the HPDC '20: The 29th International Symposium on High-Performance Parallel and Distributed Computing, 2020

2019
A Stochastic Composite Gradient Method with Incremental Variance Reduction.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

A Composite Randomized Incremental Gradient Method.
Proceedings of the 36th International Conference on Machine Learning, 2019

2018
A Sparse Completely Positive Relaxation of the Modularity Maximization for Community Detection.
SIAM J. Sci. Comput., 2018

SuperNeurons: FFT-based Gradient Sparsification in the Distributed Training of Deep Neural Networks.
CoRR, 2018

Highly accurate model for prediction of lung nodule malignancy with CT scans.
CoRR, 2018

2017
Subspace Methods with Local Refinements for Eigenvalue Computation Using Low-Rank Tensor-Train Format.
J. Sci. Comput., 2017


  Loading...