Jineng Ren
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
Jineng Ren has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Jarvis Haupt
Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA
2 shared publications - Jiayu Wang
Beijing Institute of Technology, Beijing, China
2 shared publications - Sen Liu
Fudan University, Shanghai, China
2 shared publications - Yang Xu
Fudan University, Shanghai, China
2 shared publications - Zehua Guo
Beijing Institute of Technology
2 shared publications - Chao Yao
Shaanxi Normal University
1 shared publication
Latest Publications
- Open Access
- 10 August 2026
- Published by MDPI AG in Preprints.org
A Non-Turing Computer Architecture for Artificial Intelligence Forming Multiple Dynamic Rules and Its Halting Problem
Since the beginning of modern computer history, the Turing machine has been a dominant architecture for most computational devices, which consists of three essential components: an infinite tape for input, a read/write head, and finite control. In this structure, what the head can read (i.e., binary digits and symbols) is the same as what it has written/outputted. This is actually different from the ways in which humans think or do thought/tool experiments, where inputs can be abstract symbols while outputs can be images. Compared with this architecture, the proposed architecture uses two different types of heads and tapes, one processing specific multimodal information, including images and texts, and the other processing traditional binary digits and symbols that can perform calculation, rigid concept definition, and rigid formal logic. The mapping rules among the abstract symbols and the specific images/texts can be realized by neural networks with a high accuracy rate. Logical reasoning is thus performed through the transfer of mapping rules. The statistical decidability of the Halting Problem with an imperceptibly small error rate in reasoning steps is established for this type of machine. As an example, this paper presents how the new computer architecture (what we call “Ren machine" for simplicity here) autonomously learns a distributive property/rule of multiplication in the specific domain and further uses the rule to generate a general method (mixed in both the abstract domain and the specific domain) to compute the multiplication of any positive integers based on images/texts. The machine’s strong reasoning ability is also corroborated in proving a theorem in Plane Geometry. Moreover, a robotic architecture based on Ren machine is proposed to address the challenges faced by the Vision-Language-Action (VLA) models in unsound reasoning ability and high computational cost.
- 10 August 2026
- Published by MDPI AG in Preprints.org
Open AccessA Non-Turing Computer Architecture for Artificial Intelligence Forming Multiple Dynamic Rules and Its Halting Problem
Since the beginning of modern computer history, the Turing machine has been a dominant architecture for most computational devices, which consists of three essential components: an infinite tape for input, a read/write head, and finite control. In this structure, what the head can read (i.e., binary digits and symbols) is the same as what it has written/outputted. This is actually different from the ways in which humans think or do thought/tool experiments, where inputs can be abstract symbols while outputs can be images. Compared with this architecture, the proposed architecture uses two different types of heads and tapes, one processing specific multimodal information, including images and texts, and the other processing traditional binary digits and symbols that can perform calculation, rigid concept definition, and rigid formal logic. The mapping rules among the abstract symbols and the specific images/texts can be realized by neural networks with a high accuracy rate. Logical reasoning is thus performed through the transfer of mapping rules. The statistical decidability of the Halting Problem with an imperceptibly small error rate in reasoning steps is established for this type of machine. As an example, this paper presents how the new computer architecture (what we call “Ren machine" for simplicity here) autonomously learns a distributive property/rule of multiplication in the specific domain and further uses the rule to generate a general method (mixed in both the abstract domain and the specific domain) to compute the multiplication of any positive integers based on images/texts. The machine’s strong reasoning ability is also corroborated in proving a theorem in Plane Geometry. Moreover, a robotic architecture based on Ren machine is proposed to address the challenges faced by the Vision-Language-Action (VLA) models in unsound reasoning ability and high computational cost.
- Open Access
- 24 June 2024
- Published by Springer Nature in International Journal of Computational Intelligence Systems
- Vol. 17 (1) , 1-18
Multi-agent Gradient-Based Off-Policy Actor-Critic Algorithm for Distributed Reinforcement Learning
This paper proposes a gradient-based multi-agent actor-critic algorithm for off-policy reinforcement learning using importance sampling. Our algorithm is incremental with full gradients, and its complexity per iteration scales linearly with the size of approximation features. Previous multi-agent actor-critic algorithms are limited to the on-policy setting or off-policy emphatic temporal difference (TD) learning and they do not take advantage of the advances in off-policy gradient temporal difference learning (GTD). As a theoretical contribution, we establish that the critic step of the proposed algorithm converges to the TD solution of the projected Bellman equation and the actor step converges to the set of asymptotically stable fixed points. Numerical experiments on the multi-agent generalization of the Boyan’s chain problem show that the proposed approach provides improved performances in terms of stability and convergence rate as compared with the state-of-the-art baseline algorithm.
- 24 June 2024
- Published by Springer Nature in International Journal of Computational Intelligence Systems
- Vol. 17 (1) , 1-18
Open AccessMulti-agent Gradient-Based Off-Policy Actor-Critic Algorithm for Distributed Reinforcement Learning
This paper proposes a gradient-based multi-agent actor-critic algorithm for off-policy reinforcement learning using importance sampling. Our algorithm is incremental with full gradients, and its complexity per iteration scales linearly with the size of approximation features. Previous multi-agent actor-critic algorithms are limited to the on-policy setting or off-policy emphatic temporal difference (TD) learning and they do not take advantage of the advances in off-policy gradient temporal difference learning (GTD). As a theoretical contribution, we establish that the critic step of the proposed algorithm converges to the TD solution of the projected Bellman equation and the actor step converges to the set of asymptotically stable fixed points. Numerical experiments on the multi-agent generalization of the Boyan’s chain problem show that the proposed approach provides improved performances in terms of stability and convergence rate as compared with the state-of-the-art baseline algorithm.
- 10 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cloud Computing
- Vol. 11 (3) , 2296-2311
Congestion-Aware Critical Gradient Scheduling for Distributed Machine Learning in Data Center Networks
Distributed Machine Learning (DML) is proposed not only to accelerate the training of machine learning, but also to solve the inadequate ability for handling a large amount of training data. It adopts multiple computing nodes in data center to collaboratively work in parallel at the cost of high communication overhead. Gradient Compression (GC) is introduced to reduce the communication overhead by reducing the number of synchronized gradients among computing nodes. However, existing GC solutions suffer from varying network congestion. To be specific, when some computing nodes experience high network congestion, their gradient transmission process could be significantly delayed, slowing down the entire training process. To solve the problem, we propose FLASH, a congestion-aware GC solution for DML. FLASH accelerates the training process by jointly considering the iterative approximation of machine learning and dynamic network congestion scenarios. It can maintain good training performance by adaptively adjust and schedule the number of synchronized gradients among computing nodes. We evaluate the effectiveness of FLASH using AlexNet and Resnet18 under different network congestion scenarios. Simulation results show that under the same number of training epochs, FLASH reduces training time 22-71%, maintains good accuracy, and low loss, compared with the existing memory top-K GC solution.
- 10 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cloud Computing
- Vol. 11 (3) , 2296-2311
Congestion-Aware Critical Gradient Scheduling for Distributed Machine Learning in Data Center Networks
Distributed Machine Learning (DML) is proposed not only to accelerate the training of machine learning, but also to solve the inadequate ability for handling a large amount of training data. It adopts multiple computing nodes in data center to collaboratively work in parallel at the cost of high communication overhead. Gradient Compression (GC) is introduced to reduce the communication overhead by reducing the number of synchronized gradients among computing nodes. However, existing GC solutions suffer from varying network congestion. To be specific, when some computing nodes experience high network congestion, their gradient transmission process could be significantly delayed, slowing down the entire training process. To solve the problem, we propose FLASH, a congestion-aware GC solution for DML. FLASH accelerates the training process by jointly considering the iterative approximation of machine learning and dynamic network congestion scenarios. It can maintain good training performance by adaptively adjust and schedule the number of synchronized gradients among computing nodes. We evaluate the effectiveness of FLASH using AlexNet and Resnet18 under different network congestion scenarios. Simulation results show that under the same number of training epochs, FLASH reduces training time 22-71%, maintains good accuracy, and low loss, compared with the existing memory top-K GC solution.
- 25 February 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 22 (8) , 4930-4945
SpongeTraining: Achieving High Efficiency and Accuracy for Wireless Edge-Assisted Online Distributed Learning
Edge-assisted Distributed Learning (EDL) is a popular machine learning paradigm that uses a set of distributed edge nodes to collaboratively train a machine learning model using training data. Most of existing works implicitly assume that the fixed amount of training data is pre-collected and dispatched from user devices to edge nodes. In real world, however, training data in edge nodes are collected from user devices through wireless networks, and the volume and distribution of training data in edge nodes could exhibit temporal and spatial fluctuations due to varying wireless situations (e.g., network congestion, link capacity variation). In this way, existing solutions suffer from slow convergence and low accuracy. In this paper, we propose SpongeTraining to achieve high efficiency and accuracy for online EDL. To accommodate to fluctuations in training data, SpongeTraining uses a buffer at each worker to store received training data and adaptively adjusts training batch size and learning rate of each worker based on training data extracted from the buffer. Experiment results based on real-world datasets show that SpongeTraining outperforms existing solutions by accelerating the training process up to 50% for reaching the same training accuracy.
- 25 February 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 22 (8) , 4930-4945
SpongeTraining: Achieving High Efficiency and Accuracy for Wireless Edge-Assisted Online Distributed Learning
Edge-assisted Distributed Learning (EDL) is a popular machine learning paradigm that uses a set of distributed edge nodes to collaboratively train a machine learning model using training data. Most of existing works implicitly assume that the fixed amount of training data is pre-collected and dispatched from user devices to edge nodes. In real world, however, training data in edge nodes are collected from user devices through wireless networks, and the volume and distribution of training data in edge nodes could exhibit temporal and spatial fluctuations due to varying wireless situations (e.g., network congestion, link capacity variation). In this way, existing solutions suffer from slow convergence and low accuracy. In this paper, we propose SpongeTraining to achieve high efficiency and accuracy for online EDL. To accommodate to fluctuations in training data, SpongeTraining uses a buffer at each worker to store received training data and adaptively adjusts training batch size and learning rate of each worker based on training data extracted from the buffer. Experiment results based on real-world datasets show that SpongeTraining outperforms existing solutions by accelerating the training process up to 50% for reaching the same training accuracy.
- 21 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 68 (1053587X) , 3325-3340
A Provably Communication-Efficient Asynchronous Distributed Inference Method for Convex and Nonconvex Problems
This paper proposes and analyzes a communication-efficient distributed optimization framework for general nonconvex nonsmooth signal processing and machine learning problems under an asynchronous protocol. At each iteration, worker machines compute gradients of a known empirical loss function using their own local data, and a master machine solves a related minimization problem to update the current estimate. We prove that for nonconvex nonsmooth problems, the proposed algorithm converges to a stationary point with a sublinear rate over the number of communication rounds, coinciding with the best theoretical rate that can be achieved for this class of problems. Linear convergence to a global minimum is established without any statistical assumptions on the local data for problems characterized by composite loss functions whose smooth part is strongly convex. Extensive numerical experiments verify that the performance of the proposed approach indeed improves -- sometimes significantly -- over other state-of-the-art algorithms in terms of total communication efficiency.
- 21 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 68 (1053587X) , 3325-3340
A Provably Communication-Efficient Asynchronous Distributed Inference Method for Convex and Nonconvex Problems
This paper proposes and analyzes a communication-efficient distributed optimization framework for general nonconvex nonsmooth signal processing and machine learning problems under an asynchronous protocol. At each iteration, worker machines compute gradients of a known empirical loss function using their own local data, and a master machine solves a related minimization problem to update the current estimate. We prove that for nonconvex nonsmooth problems, the proposed algorithm converges to a stationary point with a sublinear rate over the number of communication rounds, coinciding with the best theoretical rate that can be achieved for this class of problems. Linear convergence to a global minimum is established without any statistical assumptions on the local data for problems characterized by composite loss functions whose smooth part is strongly convex. Extensive numerical experiments verify that the performance of the proposed approach indeed improves -- sometimes significantly -- over other state-of-the-art algorithms in terms of total communication efficiency.
- Open Access
- 18 December 2014
- Published by Springer Nature in Journal of Inequalities and Applications
- Vol. 2014 (1) , 510
Multilinear Fourier multipliers on variable Lebesgue spaces
- 18 December 2014
- Published by Springer Nature in Journal of Inequalities and Applications
- Vol. 2014 (1) , 510
Open AccessMultilinear Fourier multipliers on variable Lebesgue spaces
- Open Access
Multilinear Fourier multipliers on variable Lebesgue spaces
In this paper, we study properties of the bilinear multiplier space. We give a necessary condition for a continuous integrable function to be a bilinear multiplier on variable exponent Lebesgue spaces. And we prove the localization theorem of multipliers on variable exponent Lebesgue spaces. Moreover, we present a Mihlin-H\"ormander type theorem for multilinear Fourier multipliers on weighted variable Lebesgue spaces and give some applications.
Open AccessMultilinear Fourier multipliers on variable Lebesgue spaces
In this paper, we study properties of the bilinear multiplier space. We give a necessary condition for a continuous integrable function to be a bilinear multiplier on variable exponent Lebesgue spaces. And we prove the localization theorem of multipliers on variable exponent Lebesgue spaces. Moreover, we present a Mihlin-H\"ormander type theorem for multilinear Fourier multipliers on weighted variable Lebesgue spaces and give some applications.