Jing Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Jing Yang has a total of 55 co-authors. Here are the top co-authors by number of shared publications:
- Cong Shen
Charles L. Brown Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, VA, USA
11 shared publications Ruiquan Huang
School of EECS The Pennsylvania State University USA
8 shared publicationsSongtao Feng
Department of Electrical and Computer Engineering The Ohio State University 43210 OH USA
7 shared publications- Yingbin Liang
Department of Electrical and Computer Engineering, The Ohio State University, Columbus, OH, USA
6 shared publications - Harold Vincent Poor
Princeton University
5 shared publications - Jingxian Wu
Department of Electrical Engineering, University of Arkansas, Fayetteville, AR, USA
4 shared publications
Latest Publications
- Open Access
- 18 May 2026
- Published byĀ Association for Computing Machinery (ACM)Ā inĀ Proceedings of the ACM on Management of Data
- Vol.Ā 4 Ā (3) , 1-26
HeteroFedSyn: Differentially Private Tabular Data Synthesis for Heterogeneous Federated Settings
Traditional Differential Privacy (DP) mechanisms are typically tailored to specific analysis tasks, which limits the reusability of protected data. DP tabular data synthesis overcomes this by generating synthetic datasets that can be shared for arbitrary downstream tasks. However, existing synthesis methods predominantly assume centralized or local settings and overlook the more practical horizontal federated scenario. NaĆÆvely synthesizing data locally or perturbing individual records either produces biased mixtures or introduces excessive noise, especially under heterogeneous data distributions across participants. We propose HeteroFedSyn, the first DP tabular data synthesis framework designed specifically for the horizontal federated setting. Built upon the PrivSyn paradigm of 2-way marginalābased synthesis, HeteroFedSyn introduces three key innovations for distributed marginal selection: (i) an l 2 -based dependency metric with random projection for noise-efficient correlation measurement, (ii) an unbiased estimator to correct multiplicative noise, and (iii) an adaptive selection strategy that dynamically updates dependency scores to avoid redundancy. Extensive experiments on range queries, Wasserstein fidelity, and machine learning tasks show that, despite the increased noise inherent to federated execution, HeteroFedSyn achieves utility comparable to centralized synthesis. Our code is open-sourced via the link.
- 18 May 2026
- Published byĀ Association for Computing Machinery (ACM)Ā inĀ Proceedings of the ACM on Management of Data
- Vol.Ā 4 Ā (3) , 1-26
Open AccessHeteroFedSyn: Differentially Private Tabular Data Synthesis for Heterogeneous Federated Settings
Traditional Differential Privacy (DP) mechanisms are typically tailored to specific analysis tasks, which limits the reusability of protected data. DP tabular data synthesis overcomes this by generating synthetic datasets that can be shared for arbitrary downstream tasks. However, existing synthesis methods predominantly assume centralized or local settings and overlook the more practical horizontal federated scenario. NaĆÆvely synthesizing data locally or perturbing individual records either produces biased mixtures or introduces excessive noise, especially under heterogeneous data distributions across participants. We propose HeteroFedSyn, the first DP tabular data synthesis framework designed specifically for the horizontal federated setting. Built upon the PrivSyn paradigm of 2-way marginalābased synthesis, HeteroFedSyn introduces three key innovations for distributed marginal selection: (i) an l 2 -based dependency metric with random projection for noise-efficient correlation measurement, (ii) an unbiased estimator to correct multiplicative noise, and (iii) an adaptive selection strategy that dynamically updates dependency scores to avoid redundancy. Extensive experiments on range queries, Wasserstein fidelity, and machine learning tasks show that, despite the increased noise inherent to federated execution, HeteroFedSyn achieves utility comparable to centralized synthesis. Our code is open-sourced via the link.
- 27 February 2026
- Published byĀ Institute of Electrical and Electronics Engineers (IEEE)Ā inĀ IEEE Transactions on Information Theory
- Vol.Ā 72 Ā (5) , 3175-3194
Differentially Private Wireless Federated Learning Using Orthogonal Sequences
We propose a privacy-preserving uplink over-the-air computation (AirComp) method, termed FLORAS, for single-input single-output (SISO) wireless federated learning (FL) systems. From the perspective of communication designs, FLORASeliminates the requirement of channel state information at the transmitters (CSIT) by leveraging the properties of orthogonal sequences. From the privacy perspective, we prove that FLORASoffers both item-level and client-level differential privacy (DP) guarantees. Moreover, by properly adjusting the system parameters, FLORAScan flexibly achieve different DP levels at no additional cost. A new FL convergence bound is derived which, combined with the privacy guarantees, allows for a smooth tradeoff between the achieved convergence rate and differential privacy levels. Experimental results demonstrate the advantages of FLORAScompared with the baseline AirComp method, and validate that the analytical results can guide the design of privacy-preserving FL with different tradeoff requirements on the model convergence and privacy levels.
- 27 February 2026
- Published byĀ Institute of Electrical and Electronics Engineers (IEEE)Ā inĀ IEEE Transactions on Information Theory
- Vol.Ā 72 Ā (5) , 3175-3194
Differentially Private Wireless Federated Learning Using Orthogonal Sequences
We propose a privacy-preserving uplink over-the-air computation (AirComp) method, termed FLORAS, for single-input single-output (SISO) wireless federated learning (FL) systems. From the perspective of communication designs, FLORASeliminates the requirement of channel state information at the transmitters (CSIT) by leveraging the properties of orthogonal sequences. From the privacy perspective, we prove that FLORASoffers both item-level and client-level differential privacy (DP) guarantees. Moreover, by properly adjusting the system parameters, FLORAScan flexibly achieve different DP levels at no additional cost. A new FL convergence bound is derived which, combined with the privacy guarantees, allows for a smooth tradeoff between the achieved convergence rate and differential privacy levels. Experimental results demonstrate the advantages of FLORAScompared with the baseline AirComp method, and validate that the analytical results can guide the design of privacy-preserving FL with different tradeoff requirements on the model convergence and privacy levels.
- 1 January 2026
- Published byĀ Institute of Electrical and Electronics Engineers (IEEE)Ā inĀ IEEE Journal on Selected Areas in Communications
- Vol.Ā 44, 5840-5855
Lean Clients, Full Accuracy: Hybrid Zeroth- and First-Order Split Federated Learning
- 1 January 2026
- Published byĀ Institute of Electrical and Electronics Engineers (IEEE)Ā inĀ IEEE Journal on Selected Areas in Communications
- Vol.Ā 44, 5840-5855
Lean Clients, Full Accuracy: Hybrid Zeroth- and First-Order Split Federated Learning
- 10 July 2025
- Published byĀ Institute of Electrical and Electronics Engineers (IEEE)Ā inĀ IEEE Transactions on Information Theory
- Vol.Ā 71 Ā (9) , 7208-7228
Robust Offline Reinforcement Learning for Non-Markovian Decision Processes
Distributionally robust offline reinforcement learning (RL) aims to find a policy that performs the best under the worst environment within an uncertainty set using an offline dataset collected from a nominal model. While recent advances in robust RL focus on Markov decision processes (MDPs), robust non-Markovian RL is limited to planning problem where the transitions in the uncertainty set are known. In this paper, we study the learning problem of robust offline non-Markovian RL. Specifically, when the nominal model admits a low-rank structure, we propose a new algorithm, featuring a novel dataset distillation and a lower confidence bound (LCB) design for robust values under different types of the uncertainty set. We also derive new dual forms for these robust values in non-Markovian RL, making our algorithm more amenable to practical implementation. By further introducing a novel type-I concentrability coefficient tailored for offline low-rank non-Markovian decision processes, we prove that our algorithm can find an$\epsilon $ -optimal robust policy using$O(1/\epsilon ^{2})$ offline samples. Moreover, we extend our algorithm to the case when the nominal model does not have specific structure. With a new type-II concentrability coefficient, the extended algorithm also enjoys polynomial sample efficiency under all different types of the uncertainty set.- 10 July 2025
- Published byĀ Institute of Electrical and Electronics Engineers (IEEE)Ā inĀ IEEE Transactions on Information Theory
- Vol.Ā 71 Ā (9) , 7208-7228
Robust Offline Reinforcement Learning for Non-Markovian Decision Processes
Distributionally robust offline reinforcement learning (RL) aims to find a policy that performs the best under the worst environment within an uncertainty set using an offline dataset collected from a nominal model. While recent advances in robust RL focus on Markov decision processes (MDPs), robust non-Markovian RL is limited to planning problem where the transitions in the uncertainty set are known. In this paper, we study the learning problem of robust offline non-Markovian RL. Specifically, when the nominal model admits a low-rank structure, we propose a new algorithm, featuring a novel dataset distillation and a lower confidence bound (LCB) design for robust values under different types of the uncertainty set. We also derive new dual forms for these robust values in non-Markovian RL, making our algorithm more amenable to practical implementation. By further introducing a novel type-I concentrability coefficient tailored for offline low-rank non-Markovian decision processes, we prove that our algorithm can find an$\epsilon $ -optimal robust policy using$O(1/\epsilon ^{2})$ offline samples. Moreover, we extend our algorithm to the case when the nominal model does not have specific structure. With a new type-II concentrability coefficient, the extended algorithm also enjoys polynomial sample efficiency under all different types of the uncertainty set.- Open Access
Decision Feedback In-Context Symbol Detection over Block-Fading Channels
Pre-trained Transformers, through in-context learning (ICL), have demonstrated exceptional capabilities to adapt to new tasks using example prompts \textit{without model update}. Transformer-based wireless receivers, where prompts consist of the pilot data in the form of transmitted and received signal pairs, have shown high estimation accuracy when pilot data are abundant. However, pilot information is often costly and limited in practice. In this work, we propose the \underline{DE}cision \underline{F}eedback \underline{IN}-Cont\underline{E}xt \underline{D}etection (DEFINED) solution as a new wireless receiver design, which bypasses channel estimation and directly performs symbol detection using the (sometimes extremely) limited pilot data. The key innovation in DEFINED is the proposed decision feedback mechanism in ICL, where we sequentially incorporate the detected symbols into the prompts to improve the detections for subsequent symbols. Extensive experiments across a broad range of wireless communication settings demonstrate that DEFINED achieves significant performance improvements, in some cases only needing a single pilot pair.
Open AccessDecision Feedback In-Context Symbol Detection over Block-Fading Channels
Pre-trained Transformers, through in-context learning (ICL), have demonstrated exceptional capabilities to adapt to new tasks using example prompts \textit{without model update}. Transformer-based wireless receivers, where prompts consist of the pilot data in the form of transmitted and received signal pairs, have shown high estimation accuracy when pilot data are abundant. However, pilot information is often costly and limited in practice. In this work, we propose the \underline{DE}cision \underline{F}eedback \underline{IN}-Cont\underline{E}xt \underline{D}etection (DEFINED) solution as a new wireless receiver design, which bypasses channel estimation and directly performs symbol detection using the (sometimes extremely) limited pilot data. The key innovation in DEFINED is the proposed decision feedback mechanism in ICL, where we sequentially incorporate the detected symbols into the prompts to improve the detections for subsequent symbols. Extensive experiments across a broad range of wireless communication settings demonstrate that DEFINED achieves significant performance improvements, in some cases only needing a single pilot pair.
- Open Access
Transformers as Game Players: Provable In-context Game-playing Capabilities of Pre-trained Models
The in-context learning (ICL) capability of pre-trained models based on the transformer architecture has received growing interest in recent years. While theoretical understanding has been obtained for ICL in reinforcement learning (RL), the previous results are largely confined to the single-agent setting. This work proposes to further explore the in-context learning capabilities of pre-trained transformer models in competitive multi-agent games, i.e., in-context game-playing (ICGP). Focusing on the classical two-player zero-sum games, theoretical guarantees are provided to demonstrate that pre-trained transformers can provably learn to approximate Nash equilibrium in an in-context manner for both decentralized and centralized learning settings. As a key part of the proof, constructional results are established to demonstrate that the transformer architecture is sufficiently rich to realize celebrated multi-agent game-playing algorithms, in particular, decentralized V-learning and centralized VI-ULCB.
Open AccessTransformers as Game Players: Provable In-context Game-playing Capabilities of Pre-trained Models
The in-context learning (ICL) capability of pre-trained models based on the transformer architecture has received growing interest in recent years. While theoretical understanding has been obtained for ICL in reinforcement learning (RL), the previous results are largely confined to the single-agent setting. This work proposes to further explore the in-context learning capabilities of pre-trained transformer models in competitive multi-agent games, i.e., in-context game-playing (ICGP). Focusing on the classical two-player zero-sum games, theoretical guarantees are provided to demonstrate that pre-trained transformers can provably learn to approximate Nash equilibrium in an in-context manner for both decentralized and centralized learning settings. As a key part of the proof, constructional results are established to demonstrate that the transformer architecture is sufficiently rich to realize celebrated multi-agent game-playing algorithms, in particular, decentralized V-learning and centralized VI-ULCB.
- Open Access
Federated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-ups
We study the problems of differentially private federated online prediction from experts against both stochastic adversaries and oblivious adversaries. We aim to minimize the average regret on $m$ clients working in parallel over time horizon $T$ with explicit differential privacy (DP) guarantees. With stochastic adversaries, we propose a Fed-DP-OPE-Stoch algorithm that achieves $\sqrt{m}$-fold speed-up of the per-client regret compared to the single-player counterparts under both pure DP and approximate DP constraints, while maintaining logarithmic communication costs. With oblivious adversaries, we establish non-trivial lower bounds indicating that collaboration among clients does not lead to regret speed-up with general oblivious adversaries. We then consider a special case of the oblivious adversaries setting, where there exists a low-loss expert. We design a new algorithm Fed-SVT and show that it achieves an $m$-fold regret speed-up under both pure DP and approximate DP constraints over the single-player counterparts. Our lower bound indicates that Fed-SVT is nearly optimal up to logarithmic factors. Experiments demonstrate the effectiveness of our proposed algorithms. To the best of our knowledge, this is the first work examining the differentially private online prediction from experts in the federated setting.Open AccessFederated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-ups
We study the problems of differentially private federated online prediction from experts against both stochastic adversaries and oblivious adversaries. We aim to minimize the average regret on $m$ clients working in parallel over time horizon $T$ with explicit differential privacy (DP) guarantees. With stochastic adversaries, we propose a Fed-DP-OPE-Stoch algorithm that achieves $\sqrt{m}$-fold speed-up of the per-client regret compared to the single-player counterparts under both pure DP and approximate DP constraints, while maintaining logarithmic communication costs. With oblivious adversaries, we establish non-trivial lower bounds indicating that collaboration among clients does not lead to regret speed-up with general oblivious adversaries. We then consider a special case of the oblivious adversaries setting, where there exists a low-loss expert. We design a new algorithm Fed-SVT and show that it achieves an $m$-fold regret speed-up under both pure DP and approximate DP constraints over the single-player counterparts. Our lower bound indicates that Fed-SVT is nearly optimal up to logarithmic factors. Experiments demonstrate the effectiveness of our proposed algorithms. To the best of our knowledge, this is the first work examining the differentially private online prediction from experts in the federated setting. - 10 May 2024
- Published byĀ Institute of Electrical and Electronics Engineers (IEEE)Ā inĀ IEEE Transactions on Wireless Communications
- Vol.Ā 23 Ā (10) , 12703-12716
Offline Reinforcement Learning for Wireless Network Optimization With Mixture Datasets
The recent development of reinforcement learning (RL) has boosted the adoption of online RL for wireless radio resource management (RRM). However, online RL algorithms require direct interactions with the environment, which may be undesirable given the potential performance loss due to the unavoidable exploration in RL. In this work, we first explore the use of offline RL algorithms in solving the RRM problem. We evaluate several state-of-the-art offline RL algorithms for a practical RRM problem that aims at maximizing a linear combination of total rates and 5-percentile rates via user scheduling. Our findings indicate that the performance of offline RL for the RRM problem is heavily contingent upon the behavior policy deployed for data collection. We propose an innovative offline RL approach utilizing heterogeneous datasets from various behavior policies. This method demonstrates that a strategic mixture of datasets enables near-optimal RL policy generation, even with suboptimal behavior policies. Additionally, we introduce two enhancements: an ensemble-based policy to augment dataset mixture training efficiency, and a novel offline-to-online strategy for seamless adaptation to new environments. Our data mixture approach achieves over 95% efficiency of an online RL agent in the absence of expert data. The ensemble algorithm notably reduces training duration by half compared to the data mixture method. Furthermore, our model, when applied with offline-to-online fine-tuning, surpasses existing benchmarks by approximately 5% in our user scheduling problem.
- 10 May 2024
- Published byĀ Institute of Electrical and Electronics Engineers (IEEE)Ā inĀ IEEE Transactions on Wireless Communications
- Vol.Ā 23 Ā (10) , 12703-12716
Offline Reinforcement Learning for Wireless Network Optimization With Mixture Datasets
The recent development of reinforcement learning (RL) has boosted the adoption of online RL for wireless radio resource management (RRM). However, online RL algorithms require direct interactions with the environment, which may be undesirable given the potential performance loss due to the unavoidable exploration in RL. In this work, we first explore the use of offline RL algorithms in solving the RRM problem. We evaluate several state-of-the-art offline RL algorithms for a practical RRM problem that aims at maximizing a linear combination of total rates and 5-percentile rates via user scheduling. Our findings indicate that the performance of offline RL for the RRM problem is heavily contingent upon the behavior policy deployed for data collection. We propose an innovative offline RL approach utilizing heterogeneous datasets from various behavior policies. This method demonstrates that a strategic mixture of datasets enables near-optimal RL policy generation, even with suboptimal behavior policies. Additionally, we introduce two enhancements: an ensemble-based policy to augment dataset mixture training efficiency, and a novel offline-to-online strategy for seamless adaptation to new environments. Our data mixture approach achieves over 95% efficiency of an online RL agent in the absence of expert data. The ensemble algorithm notably reduces training duration by half compared to the data mixture method. Furthermore, our model, when applied with offline-to-online fine-tuning, surpasses existing benchmarks by approximately 5% in our user scheduling problem.
- 29 March 2024
- Published byĀ Institute of Electrical and Electronics Engineers (IEEE)Ā inĀ IEEE Journal on Selected Areas in Information Theory
- Vol.Ā 5, 190-206
Toward General Function Approximation in Nonstationary Reinforcement Learning
Function approximation has experienced significant success in the field of reinforcement learning (RL). Despite a handful of progress on developing theory for nonstationary RL with function approximation under structural assumptions, existing work for nonstationary RL with general function approximation is still limited. In this work, we investigate two different approaches for nonstationary RL with general function approximation: confidence-set based algorithm and UCB-type algorithm. For the first approach, we introduce a new complexity measure called dynamic Bellman Eluder (DBE) for nonstationary MDPs, and then propose a confidence-set based algorithm based on the complexity metric. features the sliding window mechanism and a novel confidence set design for nonstationary MDPs. For the second approach, we propose a UCB-type algorithm following the popular least-square-value-iteration (LSVI) framework, and mitigate the computational efficiency challenge of the confidence-set based approach. features the restart mechanism and a new design of the bonus term to handle nonstationarity. The two proposed algorithms outperform the existing algorithms for nonstationary linear and tabular MDPs in the small variation budget setting. To the best of our knowledge, the two approaches are the first confidence-set based algorithm and UCB-type algorithm in the context of nonstationary MDPs.
- 29 March 2024
- Published byĀ Institute of Electrical and Electronics Engineers (IEEE)Ā inĀ IEEE Journal on Selected Areas in Information Theory
- Vol.Ā 5, 190-206
Toward General Function Approximation in Nonstationary Reinforcement Learning
Function approximation has experienced significant success in the field of reinforcement learning (RL). Despite a handful of progress on developing theory for nonstationary RL with function approximation under structural assumptions, existing work for nonstationary RL with general function approximation is still limited. In this work, we investigate two different approaches for nonstationary RL with general function approximation: confidence-set based algorithm and UCB-type algorithm. For the first approach, we introduce a new complexity measure called dynamic Bellman Eluder (DBE) for nonstationary MDPs, and then propose a confidence-set based algorithm based on the complexity metric. features the sliding window mechanism and a novel confidence set design for nonstationary MDPs. For the second approach, we propose a UCB-type algorithm following the popular least-square-value-iteration (LSVI) framework, and mitigate the computational efficiency challenge of the confidence-set based approach. features the restart mechanism and a new design of the bonus term to handle nonstationarity. The two proposed algorithms outperform the existing algorithms for nonstationary linear and tabular MDPs in the small variation budget setting. To the best of our knowledge, the two approaches are the first confidence-set based algorithm and UCB-type algorithm in the context of nonstationary MDPs.
- 22 November 2023
- Published byĀ Institute of Electrical and Electronics Engineers (IEEE)Ā inĀ IEEE Transactions on Signal Processing
- Vol.Ā 71 Ā (1053587X) , 4407-4422
Reward Teaching for Federated Multiarmed Bandits
Most of the existing federated multi-armed bandits (FMAB) designs are based on the presumption that clients will implement the specified design to collaborate with the server. In reality, however, it may not be possible to modify the clientsā existing protocols. To address this challenge, this work focuses on clients who always maximize their individual cumulative rewards, and introduces a novel idea of āreward teachingā, where the server guides the clients towards global optimality through implicit local reward adjustments. Under this framework, the server faces two tightly coupled tasks of bandit learning and target teaching, whose combination is non-trivial and challenging. A phased approach, called Teaching-After-Learning (TAL) , is first designed to encourage and discourage clientsā explorations separately. General performance analyses of TAL are established when the clientsā strategies satisfy certain mild requirements. With novel technical approaches developed to analyze the warm-start behaviors of bandit algorithms, particularized guarantees of TAL with clients running UCB or ε -greedy strategies are then obtained. These results demonstrate that TAL achieves logarithmic regrets while only incurring logarithmic adjustment costs, which is order-optimal w.r.t. a natural lower bound. As a further extension, the Teaching-While-Learning (TWL) algorithm is developed with the idea of successive arm elimination to break the non-adaptive phase separation in TAL. Rigorous analyses demonstrate that when facing clients with UCB1, TWL outperforms TAL in terms of the dependencies on sub-optimality gaps thanks to its adaptive design. Experimental results demonstrate the effectiveness and generality of the proposed algorithms.
- 22 November 2023
- Published byĀ Institute of Electrical and Electronics Engineers (IEEE)Ā inĀ IEEE Transactions on Signal Processing
- Vol.Ā 71 Ā (1053587X) , 4407-4422
Reward Teaching for Federated Multiarmed Bandits
Most of the existing federated multi-armed bandits (FMAB) designs are based on the presumption that clients will implement the specified design to collaborate with the server. In reality, however, it may not be possible to modify the clientsā existing protocols. To address this challenge, this work focuses on clients who always maximize their individual cumulative rewards, and introduces a novel idea of āreward teachingā, where the server guides the clients towards global optimality through implicit local reward adjustments. Under this framework, the server faces two tightly coupled tasks of bandit learning and target teaching, whose combination is non-trivial and challenging. A phased approach, called Teaching-After-Learning (TAL) , is first designed to encourage and discourage clientsā explorations separately. General performance analyses of TAL are established when the clientsā strategies satisfy certain mild requirements. With novel technical approaches developed to analyze the warm-start behaviors of bandit algorithms, particularized guarantees of TAL with clients running UCB or ε -greedy strategies are then obtained. These results demonstrate that TAL achieves logarithmic regrets while only incurring logarithmic adjustment costs, which is order-optimal w.r.t. a natural lower bound. As a further extension, the Teaching-While-Learning (TWL) algorithm is developed with the idea of successive arm elimination to break the non-adaptive phase separation in TAL. Rigorous analyses demonstrate that when facing clients with UCB1, TWL outperforms TAL in terms of the dependencies on sub-optimality gaps thanks to its adaptive design. Experimental results demonstrate the effectiveness and generality of the proposed algorithms.