BioGD: Bio-inspired robust gradient descent

Robust Decentralized Differentially Private Stochastic Gradient Descent

Stochastic gradient descent (SGD) is one of the most applied machine learning algorithms in unreliable large-scale decentralized environments. In this type of environment data privacy is a fundamental concern. The most popular way to investigate this topic is based on the framework of differential privacy. However, many important implementation details and the performance of differentially priv...

Bio-inspired Noise Robust Auditory Features

Bio-inspired Source Seeking with no Explicit Gradient Estimation

Inspired by behaviors of fish groups seeking darker (shaded) regions in environments with complex lighting variations, we develop distributed source-seeking algorithms for a group of sensing agents with no explicit gradient estimation. We choose a baseline for agent groups and decompose the velocity of each agent into two parts. The first part, which is perpendicular to the baseline, is chosen ...

A bio-inspired feature extraction for robust speech recognition

In this paper, a feature extraction method for robust speech recognition in noisy environments is proposed. The proposed method is motivated by a biologically inspired auditory model which simulates the outer/middle ear filtering by a low-pass filter and the spectral behaviour of the cochlea by the Gammachirp auditory filterbank (GcFB). The speech recognition performance of our method is tested...

Fast Algorithms for Robust PCA via Gradient Descent

We consider the problem of Robust PCA in the the fully and partially observed settings. Without corruptions, this is the well-known matrix completion problem. From a statistical standpoint this problem has been recently well-studied, and conditions on when recovery is possible (how many observations do we need, how many corruptions can we tolerate) via polynomialtime algorithms is by now unders...