Energetic Stable Discretization for Non-Isothermal Electrokinetics Model. (arXiv:1911.07884v1 [math.NA])

We propose an edge averaged finite element(EAFE) discretization to solve the Heat-PNP (Poisson-Nernst-Planck) equations approximately. Our method enforces positivity of the computed charged density functions and temperature function. Also the thermodynamic consistent discrete energy estimate which resembles the thermodynamic second law of the Heat-PNP system is prescribed. Numerical examples are provided.

Temporal Knowledge Graph Embedding Model based on Additive Time Series Decomposition. (arXiv:1911.07893v1 [cs.LG])

Knowledge Graph (KG) embedding has attracted more attention in recent years. Most of KG embedding models learn from time-unaware triples. However, the inclusion of temporal information beside triples would further improve the performance of a KGE model. In this regard, we propose ATiSE, a temporal KG embedding model which incorporates time information into entity/relation representations…

Efficient function approximation on general bounded domains using splines on a cartesian grid. (arXiv:1911.07894v1 [math.NA])

Functions on a bounded domain in scientific computing are often approximated using piecewise polynomial approximations on meshes that adapt to the shape of the geometry. We study the problem of function approximation using splines on a simple, regular grid that is defined on a bounding box. This approach allows the use of high order and…

A Deep Learning Approach for Robust Corridor Following. (arXiv:1911.07896v1 [cs.RO])

For an autonomous corridor following task where the environment is continuously changing, several forms of environmental noise prevent an automated feature extraction procedure from performing reliably. Moreover, in cases where pre-defined features are absent from the captured data, a well defined control signal for performing the servoing task fails to get produced. In order to…

Cooperative Multiple-Access Channels with Distributed State Information. (arXiv:1911.07899v1 [cs.IT])

This paper studies a memoryless state-dependent multiple access channel (MAC) where two transmitters wish to convey a message to a receiver under the assumption of causal and imperfect channel state information at transmitters (CSIT) and imperfect channel state information at receiver (CSIR). In order to emphasize the limitation of transmitter cooperation between physically distributed nodes,…

Improving Universal Sound Separation Using Sound Classification. (arXiv:1911.07951v1 [cs.SD])

Deep learning approaches have recently achieved impressive performance on both audio source separation and sound classification. Most audio source separation approaches focus only on separating sources belonging to a restricted domain of source classes, such as speech and music. However, recent work has demonstrated the possibility of “universal sound separation”, which aims to separate acoustic…

Alternating Between Spectral and Spatial Estimation for Speech Separation and Enhancement. (arXiv:1911.07953v1 [cs.SD])

This work investigates alternation between spectral separation using masking-based networks and spatial separation using multichannel beamforming. In this framework, the spectral separation is performed using a mask-based deep network. The result of mask-based separation is used, in turn, to estimate a spatial beamformer. The output of the beamformer is fed back into another mask-based separation…

Implicit Regularization of Normalization Methods. (arXiv:1911.07956v1 [cs.LG])

Normalization methods such as batch normalization are commonly used in overparametrized models like neural networks. Here, we study the weight normalization (WN) method (Salimans & Kingma, 2016) and a variant called reparametrized projected gradient descent (rPGD) for overparametrized least squares regression and some more general loss functions. WN and rPGD reparametrize the weights with a…

Can You Really Backdoor Federated Learning?. (arXiv:1911.07963v1 [cs.LG])

The decentralized nature of federated learning makes detecting and defending against adversarial attacks a challenging task. This paper focuses on backdoor attacks in the federated learning setting, where the goal of the adversary is to reduce the performance of the model on targeted tasks while maintaining good performance on the main task. Unlike existing works,…