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 is still suffering 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.
We present new 5 GHz VLA observations of a sample of 8 active intermediate-mass black holes with masses 104.9 < M < 106.1 M⊙ found in galaxies with stellar masses M* < 3 × 109 M⊙. 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 < 105 M⊙) 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. The 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.
Federated Averaging (FedAvg) serves as the fundamental framework in Federated Learning (FL) settings. However, we argue that 1) the multiple steps of local updating will result in gradient biases and 2) there is an inconsistency between the 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 gradient evaluation strategy. Then we introduce a meta updating procedure with a controllable meta training set to provide a clear and consistent optimization objective. Experimental results demonstrate that the proposed methods outperform compared ones with various network architectures in both the IID and non-IID FL settings.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.