XMXiaoteng Ma

Xiaoteng Ma

*This is an algorithmically generated author record based on publicly available information.

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


Xiaoteng Ma has a total of 18 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    VRCT: A Viewport Reconstruction-Based 360° Video Caching Solution for Tile-Adaptive Streaming

    by Ziwen Ye, Qing Li, Xiaoteng Ma, Dan Zhao, Yong Jiang, Lianbo Ma, Bo Yi, Gabriel-Miro Muntean

    360 $^{\circ}$ video streaming demands higher bandwidth and lower latency than conventional videos. Some solutions employ tile-adaptive 360 $^{\circ}$ video streaming and edge caching mechanisms to improve the quality of their content delivery. However, it is hard to cache large amounts of popular content with limited cache capacity. Reconstruction technologies, which have been widely adopted for images and conventional videos, can potentially reconstruct complete tile-based viewports from partial observation for 360 $^{\circ}$ videos, thus further relieving the pressure on the caching. However, it is challenging to design a flexible and efficient caching solution that supports viewport reconstruction for 360 $^{\circ}$ videos. In this paper, we propose a Viewport Reconstruction-based 360 $^{\circ}$ video Caching solution for Tile-adaptive streaming (VRCT). To enhance viewers’ quality of experience (QoE), a QoE-driven reconstruction trigger scheme is designed to determine whether to perform reconstruction or not based on current cache information and network conditions. To make efficient use of the cache space and facilitate the viewport reconstruction, a heuristic-based solution, named aggregation-based cache replacement scheme, is proposed to improve the probability of viewport reconstruction by carefully selecting which tiles to be stored in the given limited space. Through comprehensive experiments with a real head movement dataset, we show that the proposed VRCT increases the cache hit ratio by up to 29 $\%$ , reduces the backhaul usage by up to 44 $\%$ and improves user QoE by up to 32 $\%$ compared with other existing methods. In addition, experimental results show that our proposed cache replacement scheme facilitates viewport reconstruction and supports different video types.


  • Open Access

    Distributionally Robust Offline Reinforcement Learning with Linear Function Approximation

    by Xiaoteng Ma, Zhipeng Liang, Jose Blanchet, Mingwen Liu, Li Xia, Jiheng Zhang, Qianchuan Zhao, Zhengyuan Zhou

    Among the reasons hindering reinforcement learning (RL) applications to real-world problems, two factors are critical: limited data and the mismatch between the testing environment (real environment in which the policy is deployed) and the training environment (e.g., a simulator). This paper attempts to address these issues simultaneously with distributionally robust offline RL, where we learn a distributionally robust policy using historical data obtained from the source environment by optimizing against a worst-case perturbation thereof. In particular, we move beyond tabular settings and consider linear function approximation. More specifically, we consider two settings, one where the dataset is well-explored and the other where the dataset has sufficient coverage of the optimal policy. We propose two algorithms~-- one for each of the two settings~-- that achieve error bounds $\tilde{O}(d^{1/2}/N^{1/2})$ and $\tilde{O}(d^{3/2}/N^{1/2})$ respectively, where $d$ is the dimension in the linear function approximation and $N$ is the number of trajectories in the dataset. To the best of our knowledge, they provide the first non-asymptotic results of the sample complexity in this setting. Diverse experiments are conducted to demonstrate our theoretical findings, showing the superiority of our algorithm against the non-robust one.

  • Open Access

    QAVA: QoE-Aware Adaptive Video Bitrate Aggregation for HTTP Live Streaming Based on Smart Edge Computing

    by Xiaoteng Ma, Qing Li, Longhao Zou, Junkun Peng, Jianer Zhou, Jimeng Chai, Yong Jiang, Gabriel-Miro Muntean

    Currently video streaming in heterogeneous network environments is affected by limited network bandwidth availability and consequent low and variable user Quality of Experience (QoE) levels. In particular, for the case of live video streaming, a very high number of end-clients request content at the same time, generating huge concurrent traffic, and putting pressure on the existing network infrastructure. An approach which helps address this issue is deployment of emerging edge computing technologies to smooth the live streaming traffic and improve QoE by adapting client bitrates and caching content at the edge server. In this context, this paper proposes a novel Q oE-aware A daptive V ideo bitrate A ggregation scheme for HTTP live streaming based on smart edge computing (QAVA). As an intelligent proxy server, a “smart edge” which deploys QAVA aggregates all the traffic requested by clients for the same live streaming service and adapts their bitrates based on network conditions, client states and video characteristics. The adaptation is performed based on a Deep Reinforcement Learning (DRL)-based algorithm, which is also proposed. The QAVA DRL algorithm is trained and modeled based on a real client experience dataset. The experimental evaluation results presented in this paper show how QAVA outperforms other state-of-the-art adaptive bitrate algorithms in terms of average QoE and QoE fairness.


  • Learning-Based Joint QoE Optimization for Adaptive Video Streaming Based on Smart Edge

    by Xiaoteng Ma, Qing Li, Yong Jiang, Gabriel-Miro Muntean, Longhao Zou

    The latest increase in HTTP-based adaptive video streaming over the Internet enables a growing number of clients to compete for a shared bottleneck bandwidth. This competition may affect users’ Quality of Experience (QoE) negatively, especially in terms of fairness and stability. This paper presents Flex-Steward , a solution that performs multi-client joint QoE optimization for adaptive video streaming during bottleneck bandwidth sharing. Joint QoE optimization refers to improving QoE fairness among clients with various video devices and availing from differentiated services with different priorities. Flex-Steward deploys an adaptive bitrate delivery algorithm based on Neural Networks (NN) and reinforcement learning at the network edge. It relies on a trained NN model to make appropriate bitrate recommendations in terms of video chunks to be requested by clients sharing the same bottleneck bandwidth. Flex-Steward is assessed in comparison with alternative state-of-the-art algorithms under different network conditions using a real-life prototype. Results show how Flex-Steward reduces the unfairness in terms of joint QoE optimization with between 10.9% and 41.7%.