6 accepted papers
In this paper, we consider the parallel implementation of an already-trained deep model on multiple processing nodes (a.k.a. workers). Specifically, we investigate as to how a deep model should be divided into several parallel sub-models, each of which is executed efficiently by a worker. Since late…
The highly directional nature of mmWave channels results in a mutlipath incoming signal, often with varying power levels. To exploit the complete diversity of this channel, beamformer design should incorporate this multipath. This increases pilot overhead for initial access. However, low latency mmW…
Performance of the reconstruction algorithms in compressed sensing largely depends on the characteristics of measurement matrices. As such, the construction and analysis of the measurement matrix is of paramount interest. In this paper, for the first time, we focus on the class of sparse sensing mat…
We consider the problem of learning dictionaries for data compression. Different from ordinary learning methods, the objective is to design a dictionary such that the signal has a low entropy representation in the basis of the dictionary, rather than giving a sparse or low-energy representation. To…
We consider a non-stationary data stream in which the data statistics may change abruptly from one sample to another, i.e. each sample might be generated from a different (unknown) source in a mixture of K sources. The problem of identifying the models and parameters of K sources, as well as the sou…
We introduce and analyze a new technique for model reduction for deep neural networks. While large networks are theoretically capable of learning arbitrarily complex models, overfitting and model redundancy negatively affects the prediction accuracy and model variance. Our Net-Trim algorithm prunes…