arXiv subjects

Yan Zheng

Publications and source records attributed to Yan Zheng.

137 records · Page 8Linked to original sources

arXiv2018

Weighted Double Deep Multiagent Reinforcement Learning in Stochastic Cooperative Environments

Recently, multiagent deep reinforcement learning (DRL) has received increasingly wide attention. Existing multiagent DRL algorithms are inefficient when facing with the non-stationarity due to agents update their policies simultaneously in stochastic cooperative environments. This paper extends the recently proposed weighted double estimator to the multiagent domain and propose a multiagent DRL framework, named weighted double deep Q-network (WDDQN). By utilizing the weighted double estimator and the deep neural network, WDDQN can not only reduce the bias effectively but also be extended to scenarios with raw visual inputs. To achieve efficient cooperation in the multiagent domain, we introduce the lenient reward network and the scheduled replay strategy. Experiments show that the WDDQN outperforms the existing DRL and multiaent DRL algorithms, i.e., double DQN and lenient Q-learning, in terms of the average reward and the convergence rate in stochastic cooperative environments.

cs.MA↗

arXiv2018

Interactive Deep Colorization With Simultaneous Global and Local Inputs

Colorization methods using deep neural networks have become a recent trend. However, most of them do not allow user inputs, or only allow limited user inputs (only global inputs or only local inputs), to control the output colorful images. The possible reason is that it's difficult to differentiate the influence of different kind of user inputs in network training. To solve this problem, we present a novel deep colorization method, which allows simultaneous global and local inputs to better control the output colorized images. The key step is to design an appropriate loss function that can differentiate the influence of input data, global inputs and local inputs. With this design, our method accepts no inputs, or global inputs, or local inputs, or both global and local inputs, which is not supported in previous deep colorization methods. In addition, we propose a global color theme recommendation system to help users determine global inputs. Experimental results shows that our methods can better control the colorized images and generate state-of-art results.

cs.CV↗

arXiv2018

Joint convolutional neural pyramid for depth map super-resolution

High-resolution depth map can be inferred from a low-resolution one with the guidance of an additional high-resolution texture map of the same scene. Recently, deep neural networks with large receptive fields are shown to benefit applications such as image completion. Our insight is that super resolution is similar to image completion, where only parts of the depth values are precisely known. In this paper, we present a joint convolutional neural pyramid model with large receptive fields for joint depth map super-resolution. Our model consists of three sub-networks, two convolutional neural pyramids concatenated by a normal convolutional neural network. The convolutional neural pyramids extract information from large receptive fields of the depth map and guidance map, while the convolutional neural network effectively transfers useful structures of the guidance image to the depth image. Experimental results show that our model outperforms existing state-of-the-art algorithms not only on data pairs of RGB/depth images, but also on other data pairs like color/saliency and color-scribbles/colorized images.

cs.CV↗

arXiv2017

Visualization of Big Spatial Data using Coresets for Kernel Density Estimates

The size of large, geo-located datasets has reached scales where visualization of all data points is inefficient. Random sampling is a method to reduce the size of a dataset, yet it can introduce unwanted errors. We describe a method for subsampling of spatial data suitable for creating kernel density estimates from very large data and demonstrate that it results in less error than random sampling. We also introduce a method to ensure that thresholding of low values based on sampled data does not omit any regions above the desired threshold when working with sampled data. We demonstrate the effectiveness of our approach using both, artificial and real-world large geospatial datasets.

cs.HC↗

arXiv2017

Coresets for Kernel Regression

Kernel regression is an essential and ubiquitous tool for non-parametric data analysis, particularly popular among time series and spatial data. However, the central operation which is performed many times, evaluating a kernel on the data set, takes linear time. This is impractical for modern large data sets. In this paper we describe coresets for kernel regression: compressed data sets which can be used as proxy for the original data and have provably bounded worst case error. The size of the coresets are independent of the raw number of data points, rather they only depend on the error guarantee, and in some cases the size of domain and amount of smoothing. We evaluate our methods on very large time series and spatial data, and demonstrate that they incur negligible error, can be constructed extremely efficiently, and allow for great computational gains.

cs.LG↗

arXiv2017

Performance of SWIPT-based Differential Amplify-and-Forward Relaying with Direct Link

A novel asymptotic closed-form probability density function (pdf) of the two-hop (TH) link is derived for a simultaneous wireless information and power transfer based differential amplify-and-forward system. Based on the pdf, asymptotic closed-form average bit-error rate expressions of the single TH link and the TH link with direct link combined with a linear combining scheme are both derived. Monte Carlo simulations verify the analytical expressions.

cs.IT↗

arXiv2016

Homotopy cartesian diagrams in n-angulated categories

It has been proved by Bergh and Thaule that the higher mapping cone axiom is equivalent to the higher octahedral axiom for n-angulated categories. In this note, we use homotopy cartesian diagrams to give several new equivalent statements of the higher mapping cone axiom, which are applied to explain the higher octahedral axiom.

math.RT↗

arXiv2015

Subsampling in Smoothed Range Spaces

We consider smoothed versions of geometric range spaces, so an element of the ground set (e.g. a point) can be contained in a range with a non-binary value in $[0,1]$. Similar notions have been considered for kernels; we extend them to more general types of ranges. We then consider approximations of these range spaces through $\varepsilon $-nets and $\varepsilon $-samples (aka $\varepsilon$-approximations). We characterize when size bounds for $\varepsilon $-samples on kernels can be extended to these more general smoothed range spaces. We also describe new generalizations for $\varepsilon $-nets to these range spaces and show when results from binary range spaces can carry over to these smoothed ones.

cs.CG↗

arXiv2015

Restoration of tetragonal $C_4$ symmetry coexistent with filamentary superconductivity in the pressure induced intermediate phase in the iron-based superconductor Ba$_{1-x}$K$_x$Fe$_2$As$_2$

The hole doped Fe-based superconductors Ba$_{1-x}$A$_x$Fe$_2$As$_2$ (where A=Na or K) show a particular rich phase diagram. It was observed that an intermediate re-entrant tetragonal phase forms within the orthorhombic antiferromagnetically-ordered stripe-type spin density wave state above the superconducting transition [S. Avci et al., Nature Comm. 5, 3845 (2014), A. E. Böhmer et al., arXiv:1412.7038v2]. A similar intermediate phase was reported to appear if pressure is applied to underdoped Ba$_{1-x}$K$_x$Fe$_2$As$_2$ [E. Hassinger et al., Phys. Rev. B 86, 140502(R) (2012)]. Here we report data of the electric resistivity, Hall effect, specific heat, and the thermoelectrical Nernst and Seebeck coefficients measured on a Ba$_{0.85}$K$_{0.15}$Fe$_2$As$_2$ single crystal under pressure up to 5.5 GPa. The data reveals a coexistence of the intermediate phase with filamentary superconductivity. The Nernst coefficient shows a large signature of nematic order that coincides with the stripe-type spin density wave state up to optimal pressure. In the pressure-induced intermediate phase the nematic order is removed, thus confirming that its nature is a re-entrant tetragonal phase.

cond-mat.supr-con↗

arXiv2015

Geometric Inference on Kernel Density Estimates

We show that geometric inference of a point cloud can be calculated by examining its kernel density estimate with a Gaussian kernel. This allows one to consider kernel density estimates, which are robust to spatial noise, subsampling, and approximate computation in comparison to raw point sets. This is achieved by examining the sublevel sets of the kernel distance, which isomorphically map to superlevel sets of the kernel density estimate. We prove new properties about the kernel distance, demonstrating stability results and allowing it to inherit reconstruction results from recent advances in distance-based topological reconstruction. Moreover, we provide an algorithm to estimate its topology using weighted Vietoris-Rips complexes.

cs.CG↗

arXiv2014

High-Pressure Evolution of the Specific Heat of a Strongly Underdoped Ba(Fe0.963Co0.037)As2 Iron-Based Superconductor

We report specific-heat experiments under the influence of high pressure on a strongly underdoped Co-substituted BaFe2As2 single crystal. This allows us to study the phase diagram of this iron pnictide superconductor with a bulk thermodynamic method and pressure as a clean control parameter. The data show large specific-heat anomalies at the superconducting transition temperature, which proves the bulk nature of pressure-induced superconductivity. The transitions in the specific heat are sharper than in resistivity, which demonstrates the necessity of employing bulk thermodynamic methods to explore the exact phase diagram of pressure-induced Fe-based superconductors. The Tc at optimal pressure and the superconducting condensation energy are found to be larger than in optimally Co-doped samples at ambient pressure, which we attribute to a weak pair breaking effect of the Co ions.

cond-mat.supr-con↗