Abstract Variational Auto-Encoders (VAEs) are capable of learning latent representations for
high dimensional data. However, due to the iid assumption, VAEs only optimize the …

Estimating covariance matrices is a fundamental technique in various domains, most notably
in machine learning and signal processing. To tackle the challenges of extensive …

Variational inference transforms posterior inference into parametric optimization thereby
enabling the use of latent variable models where otherwise impractical. However, variational …

Many machine learning and signal processing tasks involve computing sparse
representations using an overcomplete set of features or basis vectors, with compressive …

Estimating covariance matrix from massive high-dimensional and distributed data is
significant for various real-world applications. In this paper, we propose a data-aware …

In this paper, we develop a new aggregation technique to reduce the cost of surveying. Our
method aims to jointly estimate a vector of target quantities such as public opinion or voter …

Real-time processing of physiological signals collected from wearable sensors that can be
done with low computational power is a requirement for continuous health monitoring. Such …

Variational Auto-Encoders (VAEs) have been widely applied for learning compact, low-
dimensional latent representations of high-dimensional data. When the correlation structure …

Unsupervised representation learning algorithms have been playing important roles in
machine learning and related fields. However, due to optimization intractability or lack of …