Yihan Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yihan Zhang has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Hongchang Gao
Department of Computer and Information Sciences, Temple University, Philadelphia, PA, USA
3 shared publications - Chiu C. Tan
Temple University
1 shared publication - Haibin Ling
Westlake University
1 shared publication - Jie Wu
Cloud Computing Research Institute, China Telecom
1 shared publication - Meikang Qiu
Augusta University
1 shared publication - My T. Thai
University of Florida
1 shared publication
Latest Publications
- Open Access
- 20 April 2026
- Published by Springer Nature in Machine Learning
- Vol. 115 (5) , 101
On the Communication Complexity of Decentralized Stochastic Bilevel Optimization
Stochastic bilevel optimization finds widespread applications in machine learning, including meta-learning, hyperparameter optimization, and neural architecture search. To extend stochastic bilevel optimization to distributed data, several decentralized stochastic bilevel optimization algorithms have been developed. However, existing methods often suffer from slow convergence rates and high communication costs in heterogeneous settings, limiting their applicability to real-world tasks. To address these issues, we propose two novel decentralized stochastic bilevel gradient descent algorithms based on simultaneous and alternating update strategies. Our algorithms can achieve faster convergence rates and lower communication costs than existing methods. Importantly, our convergence analyses do not rely on strong assumptions regarding heterogeneity. More importantly, our theoretical analyses clearly disclose how the computation and communication regarding the Hessian-inverse-vector product under the heterogeneous setting affects the convergence rate. To the best of our knowledge, this is the first time such favorable theoretical results have been achieved with mild assumptions in the heterogeneous setting. Furthermore, we demonstrate how to establish the convergence rate for the alternating update strategy when combined with the variance-reduced gradient. Finally, experimental results confirm the efficacy of our algorithms.
- 20 April 2026
- Published by Springer Nature in Machine Learning
- Vol. 115 (5) , 101
Open AccessOn the Communication Complexity of Decentralized Stochastic Bilevel Optimization
Stochastic bilevel optimization finds widespread applications in machine learning, including meta-learning, hyperparameter optimization, and neural architecture search. To extend stochastic bilevel optimization to distributed data, several decentralized stochastic bilevel optimization algorithms have been developed. However, existing methods often suffer from slow convergence rates and high communication costs in heterogeneous settings, limiting their applicability to real-world tasks. To address these issues, we propose two novel decentralized stochastic bilevel gradient descent algorithms based on simultaneous and alternating update strategies. Our algorithms can achieve faster convergence rates and lower communication costs than existing methods. Importantly, our convergence analyses do not rely on strong assumptions regarding heterogeneity. More importantly, our theoretical analyses clearly disclose how the computation and communication regarding the Hessian-inverse-vector product under the heterogeneous setting affects the convergence rate. To the best of our knowledge, this is the first time such favorable theoretical results have been achieved with mild assumptions in the heterogeneous setting. Furthermore, we demonstrate how to establish the convergence rate for the alternating update strategy when combined with the variance-reduced gradient. Finally, experimental results confirm the efficacy of our algorithms.
- Open Access
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 8, 7047-7055
Federated Stochastic Bilevel Optimization with Fully First-Order Gradients
Federated stochastic bilevel optimization has been actively studied in recent years due to its widespread applications in machine learning. However, most existing federated stochastic bilevel optimization algorithms require the computation of second-order Hessian and Jacobian matrices, which leads to longer running times in practice. To address these challenges, we propose a novel federated stochastic variance-reduced bilevel gradient descent algorithm that relies solely on first-order oracles. Specifically, our approach does not require the computation of second-order Hessian and Jacobian matrices, significantly reducing running time. Furthermore, we introduce a novel learning rate mechanism, i.e., a constant single-time-scale learning rate, to coordinate the update of different variables. We also present a new strategy to establish the convergence rate of our algorithm. Finally, the extensive experimental results confirm the efficacy of our proposed algorithm.
- 1 September 2025
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 8, 7047-7055
Open AccessFederated Stochastic Bilevel Optimization with Fully First-Order Gradients
Federated stochastic bilevel optimization has been actively studied in recent years due to its widespread applications in machine learning. However, most existing federated stochastic bilevel optimization algorithms require the computation of second-order Hessian and Jacobian matrices, which leads to longer running times in practice. To address these challenges, we propose a novel federated stochastic variance-reduced bilevel gradient descent algorithm that relies solely on first-order oracles. Specifically, our approach does not require the computation of second-order Hessian and Jacobian matrices, significantly reducing running time. Furthermore, we introduce a novel learning rate mechanism, i.e., a constant single-time-scale learning rate, to coordinate the update of different variables. We also present a new strategy to establish the convergence rate of our algorithm. Finally, the extensive experimental results confirm the efficacy of our proposed algorithm.
- Open Access
- 1 August 2023
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 4, 4602-4610
Communication-Efficient Stochastic Gradient Descent Ascent with Momentum Algorithms
Numerous machine learning models can be formulated as a stochastic minimax optimization problem, such as imbalanced data classification with AUC maximization. Developing efficient algorithms to optimize such kinds of problems is of importance and necessity. However, most existing algorithms restrict their focus on the single-machine setting so that they are incapable of dealing with the large communication overhead in a distributed training system. Moreover, most existing communication-efficient optimization algorithms only focus on the traditional minimization problem, failing to handle the minimax optimization problem. To address these challenging issues, in this paper, we develop two novel communication-efficient stochastic gradient descent ascent with momentum algorithms for the distributed minimax optimization problem, which can significantly reduce the communication cost via the two-way compression scheme. However, the compressed momentum makes it considerably challenging to investigate the convergence rate of our algorithms, especially in the presence of the interaction between the minimization and maximization subproblems. In this paper, we successfully addressed these challenges and established the convergence rate of our algorithms for nonconvex-strongly-concave problems. To the best of our knowledge, our algorithms are the first communication-efficient algorithm with theoretical guarantees for the minimax optimization problem. Finally, we apply our algorithm to the distributed AUC maximization problem for the imbalanced data classification task. Extensive experimental results confirm the efficacy of our algorithm in saving communication costs.
- 1 August 2023
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 4, 4602-4610
Open AccessCommunication-Efficient Stochastic Gradient Descent Ascent with Momentum Algorithms
Numerous machine learning models can be formulated as a stochastic minimax optimization problem, such as imbalanced data classification with AUC maximization. Developing efficient algorithms to optimize such kinds of problems is of importance and necessity. However, most existing algorithms restrict their focus on the single-machine setting so that they are incapable of dealing with the large communication overhead in a distributed training system. Moreover, most existing communication-efficient optimization algorithms only focus on the traditional minimization problem, failing to handle the minimax optimization problem. To address these challenging issues, in this paper, we develop two novel communication-efficient stochastic gradient descent ascent with momentum algorithms for the distributed minimax optimization problem, which can significantly reduce the communication cost via the two-way compression scheme. However, the compressed momentum makes it considerably challenging to investigate the convergence rate of our algorithms, especially in the presence of the interaction between the minimization and maximization subproblems. In this paper, we successfully addressed these challenges and established the convergence rate of our algorithms for nonconvex-strongly-concave problems. To the best of our knowledge, our algorithms are the first communication-efficient algorithm with theoretical guarantees for the minimax optimization problem. Finally, we apply our algorithm to the distributed AUC maximization problem for the imbalanced data classification task. Extensive experimental results confirm the efficacy of our algorithm in saving communication costs.