Joint Optimization Of Weights Research Articles

Continual Learning of Generative Models With Limited Data: From Wasserstein-1 Barycenter to Adaptive Coalescence.

Learning generative models is challenging for a network edge node with limited data and computing power. Since tasks in similar environments share a model similarity, it is plausible to leverage pretrained generative models from other edge nodes. Appealing to optimal transport theory tailored toward Wasserstein-1 generative adversarial networks (WGANs), this study aims to develop a framework that systematically optimizes continual learning of generative models using local data at the edge node while exploiting adaptive coalescence of pretrained generative models. Specifically, by treating the knowledge transfer from other nodes as Wasserstein balls centered around their pretrained models, continual learning of generative models is cast as a constrained optimization problem, which is further reduced to a Wasserstein-1 barycenter problem. A two-stage approach is devised accordingly: 1) the barycenters among the pretrained models are computed offline, where displacement interpolation is used as the theoretic foundation for finding adaptive barycenters via a "recursive" WGAN configuration and 2) the barycenter computed offline is used as metamodel initialization for continual learning, and then, fast adaptation is carried out to find the generative model using the local samples at the target edge node. Finally, a weight ternarization method, based on joint optimization of weights and threshold for quantization, is developed to compress the generative model further. Extensive experimental studies corroborate the effectiveness of the proposed framework.

Joint Optimization of Conceptual Rainfall-Runoff Model Parameters and Weights Attributed to Meteorological Stations

Conceptual lumped rainfall-runoff models are frequently used for various environmental problems. To put them into practice, both the model calibration method and data series of the area-averaged precipitation and air temperature are needed. In the case when data from more than one measurement station are available, first the catchment-averaged meteorological data series are usually obtained by some method, and then they are used for calibration of a lumped rainfall-runoff model. However, various optimization methods could easily be applied to simultaneously calibrate both the aggregation weights attributed to various meteorological stations to obtain a lumped meteorological data series and the rainfall-runoff model parameters. This increases the problem dimensionality but allows the optimization procedure to choose the data that are most important for the rainfall-runoff process in a particular catchment, without a priori assumptions. We test the idea using two conceptual models, HBV and GR4J, and three mutually different, relatively recently proposed Evolutionary Computation and Swarm Intelligence optimization algorithms, that are applied to three catchments located in Poland and northwestern USA. We consider two cases: with and without the model error correction applied to the rainfall-runoff models. It is shown that for the calibration period, joint optimization of the weights used to aggregate the meteorological data and the parameters of the rainfall-runoff model improves the results. However, the results for the validation period are inconclusive and depend on the model, error correction, optimization algorithm, and catchment.

Accurate WiFi Localization by Unsupervised Fusion of Extended Candidate Location Set

Fusing the predictions of multiple received signal strength (RSS)-based classifiers is an efficient strategy to mitigate the impact of the fluctuation of the RSS. However, most of the existing fusion methods exhibit two remarkable shortcomings: 1) they need to train and store offline weights by the supervised learning and 2) they directly fuse the so-called candidate location set (CLS), which is collected from the most likely location estimate of each classifier (location with the largest probability of being the true location predicted by the classifier), and thus do not fully leverage the knowledge of classifiers. In general, the fluctuation of RSS does not guarantee the location predicted by each classifier with the highest probability to be the true location, thus leading to severe performance degeneration of the existing fusion methods. To overcome the above shortcomings, we propose an accurate WiFi localization framework by unsupervised fusion of an extended CLS (ECLS). First, we train multiple classifiers by only using RSS fingerprints in the offline phase. In the online phase, instead of collecting the CLS from the trained classifiers, we construct an ECLS by augmenting CLS with other location estimates (locations with predication probability greater than a certain threshold) from each classifier. As compared with the CLS, ECLS provides a bigger fusion space that likely includes the true location of the user. Furthermore, an unsupervised fusion localization algorithm based on the ECLS is derived from the joint optimization of weights and the location of the user. Furthermore, a point of inflection searching algorithm is also proposed to intelligently construct the ECLS. Real experimental results show that our proposed algorithm is more robust to changing environments and model errors, and can significantly improve the localization accuracy without any fingerprint and hardware calibrations.