SearcharxivSearch

arXiv subjects

Tianchi Huang

Publications and source records attributed to Tianchi Huang.

17 recordsLinked to original sources

Finite Hardy Phase Theory for Power Means: An exact analytic shooting family through the Carleman parameter

For the power mean $P_t$, $t<1$, let \[ \Lambda_N(t)=\sup_{x_k>0} \frac{\sum_{n=1}^N P_t(x_1,\ldots,x_n)}{\sum_{n=1}^N x_n} \] be its finite Hardy constant. Negative powers, the geometric mean, and the usual positive-exponent Hardy inequality correspond respectively to $t<0$, $t=0$, and $0<t<1$. With the analytic parameter $q=t/(1-t)\in(-1,\infty)$, and writing $\lambda_N(q)=\Lambda_N(q/(1+q))$, we derive one exact scalar shooting map for all three regimes; its apparent singularity at $q=0$ is removable and gives the finite Carleman problem exactly. The map has a common terminal condition and its limiting vector field has a quadratic critical bottleneck at \[ y_*(q)=1+q,\qquad \Lambda_*(q)=(1+q)^{(1+q)/q}. \] We prove that there is a unique real-analytic phase $\kappa(q)$ for which the finite-defect expansion has zero cubic coefficient and, uniformly for $q$ in compact subsets of $(-1,\infty)$, for every fixed $L\ge2$, \[ \Lambda_*(q)-\lambda_N(q) =\sum_{j=2}^{L}\frac{A_j(q)}{(\log N+\kappa(q))^j} +O\!\left((\log N)^{-L-1}\right). \] In this phase-normalized scale, \[ A_2=2\pi^2(1+q)\Lambda_*,\qquad A_3=0,\qquad A_4=-\frac{\pi^2}{3}(2q^2+5q+5)A_2. \] Thus the classical Carleman and positive-Hardy leading corrections are projections of a single analytic family. At the Carleman parameter we obtain $A_2(0)=2e\pi^2$ and $A_4(0)=-(10/3)e\pi^4$; the latter is also recovered by a direct local residue calculation. The phase itself contains the global discrete defect. After phase normalization, the first coefficient involving a nonconstant discrete response is $A_5$, at order $(\log N+\kappa(q))^{-5}$.

math.CA

MSADM: Large Language Model (LLM) Assisted End-to-End Network Health Management Based on Multi-Scale Semanticization

Network device and system health management is the foundation of modern network operations and maintenance. Traditional health management methods, relying on expert identification or simple rule-based algorithms, struggle to cope with the heterogeneous networks (HNs) environment. Moreover, current state-of-the-art distributed fault diagnosis methods, which utilize specific machine learning techniques, lack multi-scale adaptivity for heterogeneous device information, resulting in unsatisfactory diagnostic accuracy for HNs. In this paper, we develop an LLM-assisted end-to-end intelligent network health management framework. The framework first proposes a multi-scale data scaling method based on unsupervised learning to address the multi-scale data problem in HNs. Secondly, we combine the semantic rule tree with the attention mechanism to propose a Multi-Scale Semanticized Anomaly Detection Model (MSADM) that generates network semantic information while detecting anomalies. Finally, we embed a chain-of-thought-based large-scale language model downstream to adaptively analyze the fault diagnosis results and create an analysis report containing detailed fault information and optimization strategies. We compare our scheme with other fault diagnosis models and demonstrate that it performs well on several metrics of network fault diagnosis.

cs.NI

HiVid: LLM-Guided Video Saliency For Content-Aware VOD And Live Streaming

Content-aware streaming requires dynamic, chunk-level importance weights to optimize subjective quality of experience (QoE). However, direct human annotation is prohibitively expensive while vision-saliency models generalize poorly. We introduce HiVid, the first framework to leverage Large Language Models (LLMs) as a scalable human proxy to generate high-fidelity weights for both Video-on-Demand (VOD) and live streaming. We address 3 non-trivial challenges: (1) To extend LLMs' limited modality and circumvent token limits, we propose a perception module to assess frames in a local context window, autoregressively building a coherent understanding of the video. (2) For VOD with rating inconsistency across local windows, we propose a ranking module to perform global re-ranking with a novel LLM-guided merge-sort algorithm. (3) For live streaming which requires low-latency, online inference without future knowledge, we propose a prediction module to predict future weights with a multi-modal time series model, which comprises a content-aware attention and adaptive horizon to accommodate asynchronous LLM inference. Extensive experiments show HiVid improves weight prediction accuracy by up to 11.5\% for VOD and 26\% for live streaming over SOTA baselines. Real-world user study validates HiVid boosts streaming QoE correlation by 14.7\%.

cs.CV

Crucible: Quantifying the Potential of Control Algorithms through LLM Agents

Control algorithms in production environments typically require domain experts to tune their parameters and logic for specific scenarios. However, existing research predominantly focuses on algorithmic performance under ideal or default configurations, overlooking the critical aspect of Tuning Potential. To bridge this gap, we introduce Crucible, an agent that employs an LLM-driven, multi-level expert simulation to turn algorithms and defines a formalized metric to quantitatively evaluate their Tuning Potential. We demonstrate Crucible's effectiveness across a wide spectrum of case studies, from classic control tasks to complex computer systems, and validate its findings in a real-world deployment. Our experimental results reveal that Crucible systematically quantifies the tunable space across different algorithms. Furthermore, Crucible provides a new dimension for algorithm analysis and design, which ultimately leads to performance improvements. Our code is available at https://github.com/thu-media/Crucible.

cs.AI

Beyond Interpretability: Exploring the Comprehensibility of Adaptive Video Streaming through Large Language Models

Over the past decade, adaptive video streaming technology has witnessed significant advancements, particularly driven by the rapid evolution of deep learning techniques. However, the black-box nature of deep learning algorithms presents challenges for developers in understanding decision-making processes and optimizing for specific application scenarios. Although existing research has enhanced algorithm interpretability through decision tree conversion, interpretability does not directly equate to developers' subjective comprehensibility. To address this challenge, we introduce \texttt{ComTree}, the first bitrate adaptation algorithm generation framework that considers comprehensibility. The framework initially generates the complete set of decision trees that meet performance requirements, then leverages large language models to evaluate these trees for developer comprehensibility, ultimately selecting solutions that best facilitate human understanding and enhancement. Experimental results demonstrate that \texttt{ComTree} significantly improves comprehensibility while maintaining competitive performance, showing potential for further advancement. The source code is available at https://github.com/thu-media/ComTree.

cs.MM

Reducing Traffic Wastage in Video Streaming via Bandwidth-Efficient Bitrate Adaptation

Bitrate adaptation (also known as ABR) is a crucial technique to improve the quality of experience (QoE) for video streaming applications. However, existing ABR algorithms suffer from severe traffic wastage, which refers to the traffic cost of downloading the video segments that users do not finally consume, for example, due to early departure or video skipping. In this paper, we carefully formulate the dynamics of buffered data volume (BDV), a strongly correlated indicator of traffic wastage, which, to the best of our knowledge, is the first time to rigorously clarify the effect of downloading plans on potential wastage. To reduce wastage while keeping a high QoE, we present a bandwidth-efficient bitrate adaptation algorithm (named BE-ABR), achieving consistently low BDV without distinct QoE losses. Specifically, we design a precise, time-aware transmission delay prediction model over the Transformer architecture, and develop a fine-grained buffer control scheme. Through extensive experiments conducted on emulated and real network environments including WiFi, 4G, and 5G, we demonstrate that BE-ABR performs well in both QoE and bandwidth savings, enabling a 60.87\% wastage reduction and a comparable, or even better, QoE, compared to the state-of-the-art methods.

cs.NI

Optimizing Adaptive Video Streaming with Human Feedback

Quality of Experience~(QoE)-driven adaptive bitrate (ABR) algorithms are typically optimized using QoE models that are based on the mean opinion score~(MOS), while such principles may not account for user heterogeneity on rating scales, resulting in unexpected behaviors. In this paper, we propose Jade, which leverages reinforcement learning with human feedback~(RLHF) technologies to better align the users' opinion scores. Jade's rank-based QoE model considers relative values of user ratings to interpret the subjective perception of video sessions. We implement linear-based and Deep Neural Network (DNN)-based architectures for satisfying both accuracy and generalization ability. We further propose entropy-aware reinforced mechanisms for training policies with the integration of the proposed QoE models. Experimental results demonstrate that Jade performs favorably on conventional metrics, such as quality and stall ratio, and improves QoE by 8.09%-38.13% in different network conditions, emphasizing the importance of user heterogeneity in QoE modeling and the potential of combining linear-based and DNN-based models for performance improvement.

cs.MM

Intermediate-mass black holes and the fundamental plane of black hole accretion

We present new 5 GHz VLA observations of a sample of 8 active intermediate-mass black holes with masses $10^{4.9} < M < 10^{6.1}\ M_{\odot}$ found in galaxies with stellar masses $M_{*} < 3 \times 10^{9}\ M_{\odot}$. We detected 5 of the 8 sources at high significance. Of the detections, 4 were consistent with a point source, and one (SDSS J095418.15+471725.1, with black hole mass $M < 10^{5}\ M_{\odot}$) clearly shows extended emission that has a jet morphology. Combining our new radio data with the black hole masses and literature X-ray measurements, we put the sources on the fundamental plane of black hole accretion. We find that the extent to which the sources agree with the fundamental plane depends on their star-forming/composite/AGN classification based on optical narrow emission line ratios. he single star-forming source is inconsistent with the fundamental plane. The three composite sources are consistent, and three of the four AGN sources are inconsistent with the fundamental plane. We argue that this inconsistency is genuine and not a result of misattributing star-formation to black hole activity. Instead, we identify the sources in our sample that have AGN-like optical emission line ratios as not following the fundamental plane and thus caution the use of the fundamental plane to estimate masses without additional constraints, such as radio spectral index, radiative efficiency, or the Eddington fraction.

astro-ph.HE

Federated Learning with Unbiased Gradient Aggregation and Controllable Meta Updating

Federated learning (FL) aims to train machine learning models in the decentralized system consisting of an enormous amount of smart edge devices. Federated averaging (FedAvg), the fundamental algorithm in FL settings, proposes on-device training and model aggregation to avoid the potential heavy communication costs and privacy concerns brought by transmitting raw data. However, through theoretical analysis we argue that 1) the multiple steps of local updating will result in gradient biases and 2) there is an inconsistency between the expected target distribution and the optimization objectives following the training paradigm in FedAvg. To tackle these problems, we first propose an unbiased gradient aggregation algorithm with the keep-trace gradient descent and the gradient evaluation strategy. Then we introduce an additional controllable meta updating procedure with a small set of data samples, indicating the expected target distribution, to provide a clear and consistent optimization objective. Both the two improvements are model- and task-agnostic and can be applied individually or together. Experimental results demonstrate that the proposed methods are faster in convergence and achieve higher accuracy with different network architectures in various FL settings.

cs.LG

Self-play Reinforcement Learning for Video Transmission

Video transmission services adopt adaptive algorithms to ensure users' demands. Existing techniques are often optimized and evaluated by a function that linearly combines several weighted metrics. Nevertheless, we observe that the given function fails to describe the requirement accurately. Thus, such proposed methods might eventually violate the original needs. To eliminate this concern, we propose \emph{Zwei}, a self-play reinforcement learning algorithm for video transmission tasks. Zwei aims to update the policy by straightforwardly utilizing the actual requirement. Technically, Zwei samples a number of trajectories from the same starting point and instantly estimates the win rate w.r.t the competition outcome. Here the competition result represents which trajectory is closer to the assigned requirement. Subsequently, Zwei optimizes the strategy by maximizing the win rate. To build Zwei, we develop simulation environments, design adequate neural network models, and invent training methods for dealing with different requirements on various video transmission scenarios. Trace-driven analysis over two representative tasks demonstrates that Zwei optimizes itself according to the assigned requirement faithfully, outperforming the state-of-the-art methods under all considered scenarios.

cs.MM

Comyco: Quality-Aware Adaptive Video Streaming via Imitation Learning

Learning-based Adaptive Bit Rate~(ABR) method, aiming to learn outstanding strategies without any presumptions, has become one of the research hotspots for adaptive streaming. However, it typically suffers from several issues, i.e., low sample efficiency and lack of awareness of the video quality information. In this paper, we propose Comyco, a video quality-aware ABR approach that enormously improves the learning-based methods by tackling the above issues. Comyco trains the policy via imitating expert trajectories given by the instant solver, which can not only avoid redundant exploration but also make better use of the collected samples. Meanwhile, Comyco attempts to pick the chunk with higher perceptual video qualities rather than video bitrates. To achieve this, we construct Comyco's neural network architecture, video datasets and QoE metrics with video quality features. Using trace-driven and real-world experiments, we demonstrate significant improvements of Comyco's sample efficiency in comparison to prior work, with 1700x improvements in terms of the number of samples required and 16x improvements on training time required. Moreover, results illustrate that Comyco outperforms previously proposed methods, with the improvements on average QoE of 7.5% - 16.79%. Especially, Comyco also surpasses state-of-the-art approach Pensieve by 7.37% on average video quality under the same rebuffering time.

cs.MM

Adversarial Feature Alignment: Avoid Catastrophic Forgetting in Incremental Task Lifelong Learning

Human beings are able to master a variety of knowledge and skills with ongoing learning. By contrast, dramatic performance degradation is observed when new tasks are added to an existing neural network model. This phenomenon, termed as \emph{Catastrophic Forgetting}, is one of the major roadblocks that prevent deep neural networks from achieving human-level artificial intelligence. Several research efforts, e.g. \emph{Lifelong} or \emph{Continual} learning algorithms, have been proposed to tackle this problem. However, they either suffer from an accumulating drop in performance as the task sequence grows longer, or require to store an excessive amount of model parameters for historical memory, or cannot obtain competitive performance on the new tasks. In this paper, we focus on the incremental multi-task image classification scenario. Inspired by the learning process of human students, where they usually decompose complex tasks into easier goals, we propose an adversarial feature alignment method to avoid catastrophic forgetting. In our design, both the low-level visual features and high-level semantic features serve as soft targets and guide the training process in multiple stages, which provide sufficient supervised information of the old tasks and help to reduce forgetting. Due to the knowledge distillation and regularization phenomenons, the proposed method gains even better performance than finetuning on the new tasks, which makes it stand out from other methods. Extensive experiments in several typical lifelong learning scenarios demonstrate that our method outperforms the state-of-the-art methods in both accuracies on new tasks and performance preservation on old tasks.

cs.LG

Federated Learning with Additional Mechanisms on Clients to Reduce Communication Costs

Federated learning (FL) enables on-device training over distributed networks consisting of a massive amount of modern smart devices, such as smartphones and IoT (Internet of Things) devices. However, the leading optimization algorithm in such settings, i.e., federated averaging (FedAvg), suffers from heavy communication costs and the inevitable performance drop, especially when the local data is distributed in a non-IID way. To alleviate this problem, we propose two potential solutions by introducing additional mechanisms to the on-device training. The first (FedMMD) is adopting a two-stream model with the MMD (Maximum Mean Discrepancy) constraint instead of a single model in vanilla FedAvg to be trained on devices. Experiments show that the proposed method outperforms baselines, especially in non-IID FL settings, with a reduction of more than 20% in required communication rounds. The second is FL with feature fusion (FedFusion). By aggregating the features from both the local and global models, we achieve higher accuracy at fewer communication costs. Furthermore, the feature fusion modules offer better initialization for newly incoming clients and thus speed up the process of convergence. Experiments in popular FL scenarios show that our FedFusion outperforms baselines in both accuracy and generalization ability while reducing the number of required communication rounds by more than 60%.

cs.LG

Reactive Video Caching via long-short-term fusion approach

Video caching has been a basic network functionality in today's network architectures. Although the abundance of caching replacement algorithms has been proposed recently, these methods all suffer from a key limitation: due to their immature rules, inaccurate feature engineering or unresponsive model update, they cannot strike a balance between the long-term history and short-term sudden events. To address this concern, we propose LA-E2, a long-short-term fusion caching replacement approach, which is based on a learning-aided exploration-exploitation process. Specifically, by effectively combining the deep neural network (DNN) based prediction with the online exploitation-exploration process through a \emph{top-k} method, LA-E2 can both make use of the historical information and adapt to the constantly changing popularity responsively. Through the extensive experiments in two real-world datasets, we show that LA-E2 can achieve state-of-the-art performance and generalize well. Especially when the cache size is small, our approach can outperform the baselines by 17.5\%-68.7\% higher in total hit rate.

cs.MM

Tiyuntsong: A Self-Play Reinforcement Learning Approach for ABR Video Streaming

Existing reinforcement learning~(RL)-based adaptive bitrate~(ABR) approaches outperform the previous fixed control rules based methods by improving the Quality of Experience~(QoE) score, as the QoE metric can hardly provide clear guidance for optimization, finally resulting in the unexpected strategies. In this paper, we propose \emph{Tiyuntsong}, a self-play reinforcement learning approach with generative adversarial network~(GAN)-based method for ABR video streaming. Tiyuntsong learns strategies automatically by training two agents who are competing against each other. Note that the competition results are determined by a set of rules rather than a numerical QoE score that allows clearer optimization objectives. Meanwhile, we propose GAN Enhancement Module to extract hidden features from the past status for preserving the information without the limitations of sequence lengths. Using testbed experiments, we show that the utilization of GAN significantly improves the Tiyuntsong's performance. By comparing the performance of ABRs, we observe that Tiyuntsong also betters existing ABR algorithms in the underlying metrics.

cs.MM

QARC: Video Quality Aware Rate Control for Real-Time Video Streaming via Deep Reinforcement Learning

Due to the fluctuation of throughput under various network conditions, how to choose a proper bitrate adaptively for real-time video streaming has become an upcoming and interesting issue. Recent work focuses on providing high video bitrates instead of video qualities. Nevertheless, we notice that there exists a trade-off between sending bitrate and video quality, which motivates us to focus on how to get a balance between them. In this paper, we propose QARC (video Quality Awareness Rate Control), a rate control algorithm that aims to have a higher perceptual video quality with possibly lower sending rate and transmission latency. Starting from scratch, QARC uses deep reinforcement learning(DRL) algorithm to train a neural network to select future bitrates based on previously observed network status and past video frames, and we design a neural network to predict future perceptual video quality as a vector for taking the place of the raw picture in the DRL's inputs. We evaluate QARC over a trace-driven emulation. As excepted, QARC betters existing approaches.

cs.MM

Delay-Constrained Rate Control for Real-Time Video Streaming with Bounded Neural Network

Rate control is widely adopted during video streaming to provide both high video qualities and low latency under various network conditions. However, despite that many work have been proposed, they fail to tackle one major problem: previous methods determine a future transmission rate as a single for value which will be used in an entire time-slot, while real-world network conditions, unlike lab setup, often suffer from rapid and stochastic changes, resulting in the failures of predictions. In this paper, we propose a delay-constrained rate control approach based on end-to-end deep learning. The proposed model predicts future bit rate not as a single value, but as possible bit rate ranges using target delay gradient, with which the transmission delay is guaranteed. We collect a large scale of real-world live streaming data to train our model, and as a result, it automatically learns the correlation between throughput and target delay gradient. We build a testbed to evaluate our approach. Compared with the state-of-the-art methods, our approach demonstrates a better performance in bandwidth utilization. In all considered scenarios, a range based rate control approach outperforms the one without range by 19% to 35% in average QoE improvement.

cs.MM