Recency predicts bursts in the evolution of author citations. (arXiv:1911.11926v1 [cs.DL])

The citations process for scientific papers has been studied extensively. But while the citations accrued by authors are the sum of the citations of their papers, translating the dynamics of citation accumulation from the paper to the author level is not trivial. Here we conduct a systematic study of the evolution of author citations, and…

Sifted Randomized Singular Value Decomposition. (arXiv:1911.11772v1 [stat.ML])

We extend the randomized singular value decomposition (SVD) algorithm \citep{Halko2011finding} to estimate the SVD of a shifted data matrix without explicitly constructing the matrix in the memory. With no loss in the accuracy of the original algorithm, the extended algorithm provides for a more efficient way of matrix factorization. The algorithm facilitates the low-rank approximation…

Stable Matrix Completion using Properly Configured Kronecker Product Decomposition. (arXiv:1911.11774v1 [stat.ML])

Matrix completion problems are the problems of recovering missing entries in a partially observed high dimensional matrix with or without noise. Such a problem is encountered in a wide range of applications such as collaborative filtering, global positioning and remote sensing. Most of the existing matrix completion algorithms assume a low rank structure of the…

Improving Polyphonic Music Models with Feature-Rich Encoding. (arXiv:1911.11775v1 [cs.SD])

This paper explores sequential modeling of polyphonic music with deep neural networks. While recent breakthroughs have focussed on network architecture, we demonstrate that the representation of the sequence can make an equally significant contribution to the performance of the model as measured by validation set loss. By extracting salient features inherent to the dataset, the…

Noise Robust Generative Adversarial Networks. (arXiv:1911.11776v1 [cs.CV])

Generative adversarial networks (GANs) are neural networks that learn data distributions through adversarial training. In intensive studies, recent GANs have shown promising results for reproducing training data. However, in spite of noise, they reproduce data with fidelity. As an alternative, we propose a novel family of GANs called noise-robust GANs (NR-GANs), which can learn a…

A Preliminary Study of Disentanglement With Insights on the Inadequacy of Metrics. (arXiv:1911.11791v1 [cs.LG])

Disentangled encoding is an important step towards a better representation learning. However, despite the numerous efforts, there still is no clear winner that captures the independent features of the data in an unsupervised fashion. In this work we empirically evaluate the performance of six unsupervised disentanglement approaches on the mpi3d toy dataset curated and released…

A fractional Brownian — Hawkes model for the Italian electricity spot market: estimation and forecasting. (arXiv:1911.11795v1 [stat.AP])

We propose a model for the description and the forecast of the gross prices of electricity in the liberalized Italian energy market via an additive two-factor model driven by both a Hawkes and a fractional Brownian processes. We discuss the seasonality, the identification of spikes and the estimates of the Hurst coefficient. After the calibration…

Asymmetric Correntropy for Robust Adaptive Filtering. (arXiv:1911.11855v1 [eess.SP])

In recent years, correntropy has been seccessfully applied to robust adaptive filtering to eliminate adverse effects of impulsive noises or outliers. Correntropy is generally defined as the expectation of a Gaussian kernel between two random variables. This definition is reasonable when the error between the two random variables is symmetrically distributed around zero. For the…

Artificial Intelligence for Diagnosis of Skin Cancer: Challenges and Opportunities. (arXiv:1911.11872v1 [eess.IV])

Recently, there has been great interest in developing Artificial Intelligence (AI) enabled computer-aided diagnostics solutions for the diagnosis of skin cancer. With the increasing incidence of skin cancers, low awareness among a growing population, and a lack of adequate clinical expertise and services, there is an immediate need for AI systems to assist clinicians in…

Schr\”odingeRNN: Generative Modeling of Raw Audio as a Continuously Observed Quantum State. (arXiv:1911.11879v1 [cs.SD])

We introduce Schr\”odingeRNN, a quantum inspired generative model for raw audio. Audio data is wave-like and is sampled from a continuous signal. Although generative modelling of raw audio has made great strides lately, relational inductive biases relevant to these two characteristics are mostly absent from models explored to date. Quantum Mechanics is a natural source…